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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to questions and inquiries

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

    the start of phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.69
    tagHelperRunner
    -0.65
     estekak
    -0.63
    tvguidetime
    -0.60
    endphp
    -0.60
     Autorizaciones
    -0.60
    ंदीखरीदारी
    -0.59
     surla
    -0.59
    Selfer
    -0.58
    انيف
    -0.58
    POSITIVE LOGITS
     kağıt
    0.37
    ortar
    0.34
     wrong
    0.33
    正解
    0.33
    ToRefresh
    0.33
     ongles
    0.33
     weak
    0.32
     easier
    0.32
     offent
    0.32
     Inscrivez
    0.32
    Act Density 0.001%

    No Known Activations