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

    Neuronpedia

    INDEX
    Explanations

    code with stray characters or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     слов
    0.75
    ご覧
    0.73
    ্টর
    0.70
    εν
    0.70
    在全球
    0.70
     මෙම
    0.70
     Sulfate
    0.69
     Inglis
    0.69
     industrious
    0.68
    các
    0.68
    POSITIVE LOGITS
    feats
    0.61
    ++]
    0.60
     digniss
    0.58
    しくは
    0.56
     maç
    0.54
    ͞
    0.52
    +}
    0.51
     quadrant
    0.51
    èvement
    0.51
     same
    0.51
    Act Density 0.019%

    No Known Activations