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

    Neuronpedia

    INDEX
    Explanations

    Miss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .kode
    -0.06
    file
    -0.06
     azt
    -0.06
    许多
    -0.06
    esa
    -0.06
     神马
    -0.06
    贸
    -0.06
    _text
    -0.06
    Colour
    -0.06
    Amount
    -0.06
    POSITIVE LOGITS
    ,J
    0.07
    etection
    0.07
    *i
    0.06
     or
    0.06
    atched
    0.06
     crush
    0.06
     tweet
    0.06
     J
    0.06
    μει
    0.06
    ufact
    0.06
    Act Density 0.001%

    No Known Activations