Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    patterns or structures related to code or programming constructs, particularly in the context of data manipulation or control flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A colon, "of," or "in" followed by a likely word

    np_acts-logits-general · gemini-2.0-flash

    iterating through collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.84
    verwijspagina
    -0.81
    دانشنامهٔ
    -0.74
    SequentialGroup
    -0.71
     للاسماء
    -0.70
    ConstraintMaker
    -0.68
    transQ
    -0.66
     Roskov
    -0.63
    رشف
    -0.61
    Diweddarwch
    -0.60
    POSITIVE LOGITS
     the
    0.44
     our
    0.42
     anggota
    0.42
    dataProvider
    0.42
     listed
    0.41
     members
    0.41
    InOrder
    0.38
     list
    0.38
     we
    0.37
     Lin
    0.37
    Act Density 0.130%

    No Known Activations