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

    Neuronpedia

    INDEX
    Explanations

    cells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    こちら
    -0.07
    [Y
    -0.07
     Raum
    -0.07
    valid
    -0.07
     café
    -0.07
    しない
    -0.07
     Fer
    -0.07
    .Encode
    -0.06
     zim
    -0.06
     Québec
    -0.06
    POSITIVE LOGITS
    emouth
    0.07
    _rev
    0.07
    inf
    0.06
    .flush
    0.06
     док
    0.06
     repl
    0.06
     Сов
    0.06
    ipping
    0.06
    ves
    0.06
    yped
    0.06
    Act Density 0.008%

    No Known Activations