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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一
    1.18
     an
    1.11
    أ
    1.02
     was
    1.00
     å
    0.94
    ER
    0.91
    LE
    0.91
     på
    0.88
     för
    0.86
     à
    0.85
    POSITIVE LOGITS
     stesse
    0.94
     mismas
    0.93
    lerine
    0.92
    ല്ലാം
    0.91
     are
    0.89
    ll
    0.88
    li
    0.87
     rupani
    0.87
     deportivas
    0.87
     financieras
    0.87
    Act Density 1.503%

    No Known Activations