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

    Neuronpedia

    INDEX
    Explanations

    code structures and syntax related to class definitions and method declarations

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

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indefinitely
    -0.40
    lijker
    -0.38
     scarce
    -0.38
     pah
    -0.36
     already
    -0.36
     ovan
    -0.35
     befür
    -0.35
    Gilla
    -0.34
    roppo
    -0.34
     eternally
    -0.34
    POSITIVE LOGITS
     endblock
    0.63
    TagMode
    0.62
    ьаж
    0.59
     consultato
    0.59
    Geplaatst
    0.57
    InitVars
    0.56
    GEBURTSDATUM
    0.56
     للمعارف
    0.55
    KURZBESCHREIBUNG
    0.54
    IBAction
    0.54
    Act Density 0.009%

    No Known Activations