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

    Neuronpedia

    INDEX
    Explanations

    Code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     मामलों
    -0.08
    au
    -0.08
    ാഭ്യാസ
    -0.08
     humiliation
    -0.08
     epochs
    -0.08
    epoch
    -0.08
    asis
    -0.08
    abila
    -0.08
    loge
    -0.08
     originals
    -0.08
    POSITIVE LOGITS
     específico
    0.09
     generic
    0.08
     typings
    0.08
     producido
    0.08
     специф
    0.08
     泛
    0.08
     vaat
    0.08
     cast
    0.08
     typing
    0.08
     keyof
    0.08
    Act Density 0.007%

    No Known Activations