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

    Neuronpedia

    INDEX
    Explanations

    Dutch general, ladies, registration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endereco
    -0.76
     Erkrank
    -0.73
     drugie
    -0.72
    limia
    -0.71
    авто
    -0.70
     Хе
    -0.70
    flink
    -0.68
     Highlight
    -0.68
     Stable
    -0.66
    enforce
    -0.66
    POSITIVE LOGITS
     Können
    0.81
    Domic
    0.81
     schneiden
    0.79
    ὴ
    0.79
     functor
    0.79
    ättning
    0.78
     همیشه
    0.77
     الخام
    0.76
     Publikum
    0.76
    iertamente
    0.73
    Act Density 0.033%

    No Known Activations