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

    Neuronpedia

    INDEX
    Explanations

    ANY KIND

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    香
    -0.81
    Michael
    -0.76
    生物
    -0.75
    Ni
    -0.75
     censiti
    -0.73
    خ
    -0.71
    CAP
    -0.69
     gratuito
    -0.68
    智能
    -0.67
    大多
    -0.67
    POSITIVE LOGITS
    LETTERS
    0.68
    ั่ว
    0.68
    Conclusión
    0.67
    deliver
    0.67
    Frente
    0.67
    dillas
    0.66
    Fuji
    0.65
    Mucho
    0.65
    OVERALL
    0.65
    ciple
    0.65
    Act Density 0.039%

    No Known Activations