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

    Neuronpedia

    INDEX
    Explanations

    decision making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هما
    0.79
    D
    0.77
    kk
    0.71
    P
    0.70
     nisso
    0.69
    resso
    0.67
    ಿಗ
    0.66
    C
    0.66
    =>$
    0.65
    F
    0.65
    POSITIVE LOGITS
     Thời
    0.86
    ن
    0.79
    н
    0.75
     далі
    0.73
     ওমর
    0.70
     결정
    0.70
     돈
    0.69
     感
    0.66
     요구
    0.66
    т
    0.66
    Act Density 0.001%

    No Known Activations