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

    Neuronpedia

    INDEX
    Explanations

    falling into wrong hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.92
    য়
    0.64
    一
    0.59
     ষে
    0.56
     در
    0.54
    ه‌ها
    0.54
    ల్
    0.54
     أ
    0.53
    𝙥
    0.53
    There
    0.50
    POSITIVE LOGITS
    -
    0.84
     I
    0.81
    ia
    0.79
     Hands
    0.74
     hands
    0.72
     Tecnologia
    0.62
    ed
    0.58
     manos
    0.58
     Optimum
    0.58
     H
    0.58
    Act Density 0.001%

    No Known Activations