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

    Neuronpedia

    INDEX
    Explanations

    the presence of text content within a document

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.85
    Personendaten
    -0.84
     Мексичка
    -0.81
    MessageOf
    -0.76
     HasFactory
    -0.73
    enterOuterAlt
    -0.73
    AndEndTag
    -0.72
     invokingState
    -0.70
    ViewFeatures
    -0.69
    دانشنامهٔ
    -0.69
    POSITIVE LOGITS
     («
    0.30
    laquo
    0.29
    </h6>
    0.28
    Acta
    0.28
    *
    0.27
    sc
    0.26
     ак
    0.26
    Jeux
    0.26
     (“
    0.25
    ‐
    0.25
    Act Density 0.000%

    No Known Activations