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

    Neuronpedia

    INDEX
    Explanations

    file or select

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     messo
    0.88
     personnalisé
    0.84
     ridicul
    0.83
     шеран
    0.82
     mogen
    0.82
     transparencia
    0.81
     serviço
    0.79
    utom
    0.79
     personalizados
    0.78
     personalizada
    0.77
    POSITIVE LOGITS
     Kn
    0.68
    ก
    0.65
     Kand
    0.62
    Mat
    0.60
    Ball
    0.60
    ல்
    0.59
     Cand
    0.59
    pkl
    0.59
     Bom
    0.59
     Input
    0.58
    Act Density 0.004%

    No Known Activations