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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration and positivity towards creativity

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

    user turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.78
    OGND
    -0.77
     للاسماء
    -0.76
    الحياه
    -0.76
     Мексичка
    -0.75
     PeEnEo
    -0.75
    تقاوى
    -0.75
    səhifə
    -0.73
     мәкалә
    -0.72
     estekak
    -0.71
    POSITIVE LOGITS
     simpat
    0.31
    Super
    0.30
    super
    0.29
     Nic
    0.28
     perfect
    0.28
     Super
    0.28
    AutoScale
    0.28
     sweet
    0.28
    phi
    0.28
    rie
    0.27
    Act Density 0.003%

    No Known Activations