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

    Neuronpedia

    INDEX
    Explanations

    program rating narrative novel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    挺
    0.38
    濡
    0.37
    Flora
    0.37
     dubious
    0.36
     لائن
    0.36
     Instinct
    0.35
    antung
    0.35
     Hound
    0.34
     Monst
    0.34
    韦
    0.34
    POSITIVE LOGITS
    ндекс
    0.40
    рет
    0.39
     उपभो
    0.38
     крово
    0.38
    ︹
    0.38
    ړه
    0.38
     clor
    0.38
     consumidores
    0.38
    PostBody
    0.38
     पूछता
    0.38
    Act Density 0.001%

    No Known Activations