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

    Neuronpedia

    INDEX
    Explanations

    sentence terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.87
    s
    0.70
    is
    0.69
    et
    0.68
    '
    0.62
    스를
    0.59
    有两个
    0.56
    τε
    0.55
    ط
    0.55
    合計
    0.54
    POSITIVE LOGITS
     juiste
    0.64
     ו
    0.61
     വൈദ്യുതി
    0.60
     thine
    0.59
     गाने
    0.58
     !")
    0.58
     montañas
    0.58
    water
    0.57
    iritual
    0.57
     piante
    0.56
    Act Density 0.094%

    No Known Activations