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

    Neuronpedia

    INDEX
    Explanations

    written text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tarafından
    -0.07
     Pane
    -0.07
    odo
    -0.07
    <textarea
    -0.07
    思想政治
    -0.07
     contestants
    -0.07
    进城
    -0.07
    蔷
    -0.07
     hurl
    -0.06
    raj
    -0.06
    POSITIVE LOGITS
    见证了
    0.07
     helped
    0.07
    (cap
    0.06
    ację
    0.06
    .Server
    0.06
     monet
    0.06
    連續
    0.06
     Linked
    0.06
     optimized
    0.06
    מת
    0.06
    Act Density 0.000%

    No Known Activations