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

    Neuronpedia

    INDEX
    Explanations

    people, categories, and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adio
    0.91
    byshev
    0.88
    ulter
    0.88
    estine
    0.86
    voltage
    0.83
    înes
    0.83
    ing
    0.83
    enegro
    0.81
     उक्त
    0.81
    );
    0.80
    POSITIVE LOGITS
    ل
    1.02
     soorten
    0.98
    0.98
     quienes
    0.96
     வகைகள்
    0.93
     viendo
    0.92
     Vieni
    0.92
     देखकर
    0.91
    시는
    0.91
    ਨ
    0.91
    Act Density 1.106%

    No Known Activations