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

    Neuronpedia

    INDEX
    Explanations

    body parts and mind concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hands
    0.79
    圭
    0.73
    嘴角
    0.71
     руках
    0.68
     कुंडली
    0.67
     കൈ
    0.67
     глаз
    0.67
    theoretic
    0.65
     আপন
    0.65
     UIP
    0.64
    POSITIVE LOGITS
    prints
    1.22
    print
    1.07
    aches
    1.07
    ache
    1.06
    washing
    1.04
    guards
    0.99
    candy
    0.99
     candy
    0.97
    wash
    0.94
    piece
    0.93
    Act Density 0.229%

    No Known Activations