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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical results from a research context

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

    Numbers containing "9" and followed by a comma or period

    np_acts-logits-general · gemini-2.0-flash

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.82
    Tikang
    -0.77
    ymce
    -0.68
    IMPORTED
    -0.66
    المكان
    -0.66
     SwitchCompat
    -0.63
    withIdentifier
    -0.63
    parsedMessage
    -0.62
     المعرف
    -0.62
     برانيه
    -0.62
    POSITIVE LOGITS
     Bernhard
    0.44
     Reynolds
    0.42
    くちゃ
    0.42
     FE
    0.42
    fea
    0.41
     Nelly
    0.41
    ="//
    0.41
     Arnold
    0.41
    NH
    0.40
     Barnard
    0.40
    Act Density 1.633%

    No Known Activations