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

    Neuronpedia

    INDEX
    Explanations

    write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وو
    -0.08
    龄
    -0.06
    greens
    -0.06
    ampo
    -0.06
    experiment
    -0.06
    レビ
    -0.06
    ENS
    -0.06
    SMART
    -0.06
     onCancelled
    -0.06
    Opts
    -0.06
    POSITIVE LOGITS
    	B
    0.07
    Sil
    0.06
    [len
    0.06
    Modificar
    0.06
    단체
    0.06
    .Root
    0.06
    (mat
    0.06
     Вони
    0.06
    435
    0.06
    .sync
    0.06
    Act Density 0.159%

    No Known Activations