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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    token
    -0.06
    .Body
    -0.06
    itan
    -0.06
     popped
    -0.06
    config
    -0.06
    cobra
    -0.06
    Did
    -0.06
     odds
    -0.06
    뿐
    -0.06
     salah
    -0.06
    POSITIVE LOGITS
    .WebControls
    0.07
     Increases
    0.06
    .");
    0.06
     درخواست
    0.06
     Βασ
    0.06
     Hann
    0.06
     extents
    0.06
    ofi
    0.06
    콜
    0.06
    .setTextSize
    0.06
    Act Density 0.011%

    No Known Activations