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

    Neuronpedia

    INDEX
    Explanations

    theoretical frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нення
    0.74
    க்கி
    0.73
    ються
    0.73
    ній
    0.69
    ">(</
    0.69
    ه‌ای
    0.69
     nouvelles
    0.67
    の変化
    0.67
    I
    0.67
    вання
    0.67
    POSITIVE LOGITS
    ka
    0.79
    ش
    0.77
    os
    0.76
    es
    0.74
    x
    0.73
    ar
    0.72
    kk
    0.72
     Shooter
    0.70
    ج
    0.69
    ot
    0.66
    Act Density 0.002%

    No Known Activations