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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotions and values, particularly joy and compassion

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

    Abstract positive nouns

    np_acts-logits-general · gemini-2.0-flash

    states and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.84
    ]<<"
    -0.71
     Вікіпе
    -0.66
    Geplaatst
    -0.65
    锈钢
    -0.63
     hornblende
    -0.63
    WithFormat
    -0.62
    ViewImports
    -0.62
    úgó
    -0.62
    "]="
    -0.61
    POSITIVE LOGITS
    fulness
    0.70
     רבה
    0.64
    ValueStyle
    0.62
     incarnate
    0.55
     רב
    0.53
    ful
    0.53
     humaine
    0.53
     galore
    0.53
     autorytatywna
    0.52
    lessness
    0.52
    Act Density 0.518%

    No Known Activations