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

    Neuronpedia

    INDEX
    Explanations

    static import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     balcony
    0.71
     glider
    0.71
     secretly
    0.66
     Himself
    0.65
     downhill
    0.64
     hesitate
    0.64
     Extrem
    0.64
     walkways
    0.63
     hillside
    0.63
     dieting
    0.62
    POSITIVE LOGITS
     axi
    0.65
     中
    0.62
     authors
    0.62
    为
    0.62
    )^
    0.61
    androidx
    0.60
    如果
    0.60
    达到了
    0.60
    文献
    0.58
     yazı
    0.58
    Act Density 0.000%

    No Known Activations