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

    Neuronpedia

    INDEX
    Explanations

    confirm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sort
    -0.07
     limite
    -0.07
    だった
    -0.07
     casos
    -0.06
     yol
    -0.06
     ام
    -0.06
     Impro
    -0.06
     UTIL
    -0.06
    $options
    -0.06
     KBS
    -0.06
    POSITIVE LOGITS
     курс
    0.07
     Stunning
    0.07
     anda
    0.06
     Dresden
    0.06
    ías
    0.06
    .confirm
    0.06
    adr
    0.06
     sprayed
    0.06
    ै?
    0.06
    using
    0.06
    Act Density 0.003%

    No Known Activations