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

    Neuronpedia

    INDEX
    Explanations

    laws and regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Федераль
    -0.07
    وره
    -0.06
     youre
    -0.06
    Token
    -0.06
    _are
    -0.06
     altura
    -0.06
    Output
    -0.06
    xBE
    -0.06
     citas
    -0.06
     delivered
    -0.06
    POSITIVE LOGITS
    (withIdentifier
    0.07
     мед
    0.07
    ielding
    0.06
     Phong
    0.06
     Es
    0.06
     Chem
    0.06
     books
    0.06
     Protector
    0.06
    昇
    0.06
    .Filter
    0.06
    Act Density 0.013%

    No Known Activations