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

    Neuronpedia

    INDEX
    Explanations

    sections of the text with significant numerical or structured information

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

    Follows prepositions or numbers

    np_acts-logits-general · gemini-2.0-flash

    necessary to ensure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    -0.59
    Tipo
    -0.57
    parseColor
    -0.55
     research
    -0.55
     types
    -0.55
     solicit
    -0.54
     Tri
    -0.54
     type
    -0.53
     provide
    -0.53
    omia
    -0.53
    POSITIVE LOGITS
    AndEndTag
    1.04
    setVerticalGroup
    0.93
    RegressionTest
    0.87
    djangoproject
    0.81
     supérieurs
    0.77
     ainfi
    0.76
    LookAnd
    0.76
     quelcon
    0.76
     quæ
    0.76
     religieuses
    0.75
    Act Density 0.074%

    No Known Activations