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

    Neuronpedia

    INDEX
    Explanations

    view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,is
    -0.07
     Aud
    -0.07
    故
    -0.06
    |
    -0.06
     jap
    -0.06
    Aud
    -0.06
    ون
    -0.06
    ，以
    -0.06
    TE
    -0.06
     организ
    -0.06
    POSITIVE LOGITS
    NSData
    0.08
    DDL
    0.08
     unrest
    0.07
     دسته
    0.07
    brahim
    0.07
     восстанов
    0.06
    azioni
    0.06
    puted
    0.06
    nul
    0.06
    ufig
    0.06
    Act Density 0.068%

    No Known Activations