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

    Neuronpedia

    INDEX
    Explanations

    keys and passwords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Temos
    0.93
     hơi
    0.86
    imming
    0.82
     of
    0.81
     কোনটা
    0.81
    ieu
    0.81
    és
    0.80
    ere
    0.80
    Το
    0.79
     laps
    0.77
    POSITIVE LOGITS
    ра
    0.90
    +\
    0.90
    פ
    0.86
    ྃ
    0.80
    tenant
    0.78
    니아
    0.78
    ба
    0.77
    ⵕ
    0.77
     पासवर्ड
    0.76
     ২৯
    0.75
    Act Density 0.188%

    No Known Activations