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

    Neuronpedia

    INDEX
    Explanations

    reacting or responding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ப்ஸ்
    0.85
    چه
    0.78
    d
    0.78
    ger
    0.72
    san
    0.70
    ্যাপ
    0.70
    dor
    0.69
    gern
    0.68
    al
    0.68
    ed
    0.66
    POSITIVE LOGITS
    LastGen
    1.14
    拡散方程式
    1.06
    Alla
    0.98
     ква
    0.93
     timeCounter
    0.91
    iveness
    0.91
    motionProxy
    0.90
     tcpHeader
    0.90
     عکس
    0.89
     Yesterday
    0.89
    Act Density 0.183%

    No Known Activations