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

    Neuronpedia

    INDEX
    Explanations

    best values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nons
    0.41
     options
    0.39
    蔬
    0.38
    鼻子
    0.38
    彼
    0.37
     ছোট
    0.36
    benius
    0.36
    ｬ
    0.36
     AED
    0.36
    Persistence
    0.36
    POSITIVE LOGITS
     tarihi
    0.48
     кандай
    0.44
     mejor
    0.42
     swearing
    0.42
     fútbol
    0.39
     futbol
    0.39
     migliori
    0.39
     voetbal
    0.39
     annuel
    0.38
     mejores
    0.38
    Act Density 0.000%

    No Known Activations