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

    Neuronpedia

    INDEX
    Explanations

    html head tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findById
    0.51
    من
    0.43
    ？」
    0.41
     Bef
    0.41
    SQLException
    0.40
     بینی
    0.40
    になる
    0.40
     படங்களில்
    0.39
    why
    0.38
    uft
    0.38
    POSITIVE LOGITS
     mises
    0.46
     తప్ప
    0.45
    thora
    0.44
     приме
    0.44
    line
    0.43
    rüstung
    0.42
     pengaturan
    0.41
     necessità
    0.40
    の発
    0.40
    }^*
    0.40
    Act Density 0.001%

    No Known Activations