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

    Neuronpedia

    INDEX
    Explanations

    ./ followed by module names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.62
     tensile
    0.60
     hectare
    0.59
     viscosity
    0.58
     lymphocytic
    0.58
     cloves
    0.57
     tassel
    0.55
     cisplatin
    0.55
    of
    0.54
     effluent
    0.54
    POSITIVE LOGITS
    其他
    0.70
    ي
    0.66
     четы
    0.58
    ваш
    0.58
     ሌሎች
    0.57
    ](./
    0.56
    ../
    0.56
    ../../../
    0.55
     लागि
    0.55
    يش
    0.54
    Act Density 0.007%

    No Known Activations