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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hall
    -0.08
    .Special
    -0.06
     purs
    -0.06
    ่อง
    -0.06
     Surre
    -0.06
     WR
    -0.06
    emit
    -0.06
     ga
    -0.06
    ابق
    -0.06
    pdo
    -0.06
    POSITIVE LOGITS
     relação
    0.07
     xếp
    0.07
    loating
    0.06
     všechny
    0.06
     Erotische
    0.06
     coraz
    0.06
     appart
    0.06
     prise
    0.06
     Floating
    0.06
    434
    0.06
    Act Density 0.000%

    No Known Activations