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

    Neuronpedia

    INDEX
    Explanations

    start of model response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     here
    0.90
    here
    0.80
    这里
    0.69
     здесь
    0.67
     هنا
    0.66
     ici
    0.64
    !
    0.63
    click
    0.62
    活力
    0.62
     Here
    0.61
    POSITIVE LOGITS
    もお
    0.92
     antire
    0.82
    铌
    0.78
    ånd
    0.78
     ಲೋ
    0.78
     morphisms
    0.77
    我们也
    0.77
     religi
    0.76
     şunu
    0.76
     Reader
    0.75
    Act Density 0.180%

    No Known Activations