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

    Neuronpedia

    INDEX
    Explanations

    civilian life and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.80
    ının
    0.76
     to
    0.73
    ु
    0.72
    ala
    0.71
    ра
    0.71
     P
    0.70
     fervor
    0.70
     ہیں
    0.69
    amble
    0.69
    POSITIVE LOGITS
    ج
    0.99
    א
    0.97
    ون
    0.91
    k
    0.84
    你
    0.81
    سي
    0.79
    كان
    0.79
    一
    0.78
     sozial
    0.77
    ود
    0.77
    Act Density 0.001%

    No Known Activations