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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quietly
    -0.08
    utely
    -0.07
     без
    -0.07
     independently
    -0.07
     comfortably
    -0.07
     to
    -0.07
     compart
    -0.07
     независимо
    -0.07
     regularly
    -0.07
     наконец
    -0.07
    POSITIVE LOGITS
    Enviar
    0.09
    sexo
    0.08
    ෙස
    0.08
    Sex
    0.08
     dû
    0.08
    ayna
    0.08
     ][
    0.08
     apellido
    0.08
    หรือ
    0.08
     Augustine
    0.08
    Act Density 0.010%

    No Known Activations