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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistics or measurements

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

    numbers and percentages involving zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.48
    Kanpo
    -0.48
     helping
    -0.47
     ModelExpression
    -0.47
     puentes
    -0.46
     autorytatywna
    -0.43
     assisting
    -0.42
     esimer
    -0.42
     Ergänzung
    -0.42
     enabling
    -0.42
    POSITIVE LOGITS
    0
    0.64
    2
    0.51
    qq
    0.50
    Configurer
    0.48
     noqa
    0.46
    8
    0.46
    Account
    0.46
     goog
    0.46
    1
    0.46
    **
    0.45
    Act Density 0.102%

    No Known Activations