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

    Neuronpedia

    INDEX
    Explanations

    say "ad"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Beschreibung
    -0.10
    Opis
    -0.09
    Descripción
    -0.09
     Beschreibung
    -0.08
    Env
    -0.08
     acción
    -0.08
    Descripcion
    -0.08
    Descrição
    -0.08
    Eles
    -0.08
    Kab
    -0.08
    POSITIVE LOGITS
    ad
    0.14
    .ad
    0.11
    (ad
    0.10
    	ad
    0.10
    qqu
    0.09
    ಾಡ
    0.09
    'ad
    0.09
    �
    0.09
    an
    0.09
    ('').
    0.09
    Act Density 0.002%

    No Known Activations