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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or uncertainty about an action or task

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

    asking what is missing or wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.60
     חיצוניים
    -0.55
     surla
    -0.52
    ✨:
    -0.51
     للاسماء
    -0.49
    Manbalar
    -0.49
    WithMany
    -0.48
     Roskov
    -0.48
     BoxFit
    -0.47
    principalColumn
    -0.47
    POSITIVE LOGITS
    myself
    0.37
    Inputs
    0.37
     hamp
    0.36
    0.35
     or
    0.35
    embeds
    0.35
    тъ
    0.35
     kinh
    0.35
     Fah
    0.35
    ModelState
    0.35
    Act Density 0.038%

    No Known Activations