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

    Neuronpedia

    INDEX
    Explanations

    creative text formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Parts
    0.79
     limité
    0.79
     частей
    0.77
    ুদের
    0.76
     limit
    0.74
     parts
    0.73
     Mode
    0.71
     মেশ
    0.70
    ம்ம
    0.70
     Digital
    0.69
    POSITIVE LOGITS
    сант
    0.77
    subsubsection
    0.75
    quả
    0.75
    ISTICS
    0.75
    abilità
    0.70
    之事
    0.68
    ಿಸಿದರು
    0.68
    having
    0.68
    0.68
    <unused2180>
    0.67
    Act Density 0.007%

    No Known Activations