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

    Neuronpedia

    INDEX
    Explanations

    hindu deities like Ganesha and Durga

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ти
    0.88
    ;
    0.84
    م
    0.83
    д
    0.83
    他
    0.80
    ا
    0.75
    র
    0.71
    ά
    0.71
    ка
    0.70
    一
    0.70
    POSITIVE LOGITS
    book
    0.69
     bokeh
    0.64
    callback
    0.64
    bau
    0.63
    emb
    0.62
     sealant
    0.62
     will
    0.62
    ene
    0.61
     biodegradation
    0.61
     acque
    0.60
    Act Density 0.000%

    No Known Activations