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

    Neuronpedia

    INDEX
    Explanations

    transformers import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佯
    0.72
     جائز
    0.69
    Gam
    0.67
     temple
    0.67
    ┴
    0.65
    邉
    0.65
    朩
    0.64
    样
    0.64
     signe
    0.63
     saga
    0.63
    POSITIVE LOGITS
    istration
    0.73
     Stable
    0.69
    ល
    0.65
     abbreviations
    0.64
     Strip
    0.63
    క్స్
    0.63
    体积
    0.63
     реали
    0.62
    愀
    0.62
     atan
    0.61
    Act Density 0.014%

    No Known Activations