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

    Neuronpedia

    INDEX
    Explanations

    interactive question phrases

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

    user input starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.57
     ब्रेकडाउन
    -0.54
     Reſ
    -0.54
     itſelf
    -0.53
     purpoſe
    -0.53
     Conſ
    -0.53
    masing
    -0.52
     '\\;'
    -0.52
     surla
    -0.52
     ModelExpression
    -0.50
    POSITIVE LOGITS
     bayar
    0.40
    RSpec
    0.40
    OCCURRED
    0.38
     للمعارف
    0.36
     autorytatywna
    0.36
    何度
    0.36
    Que
    0.36
     Mey
    0.35
    ORAGE
    0.34
     muối
    0.34
    Act Density 0.006%

    No Known Activations