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

    Neuronpedia

    INDEX
    Explanations

    ography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servicios
    -0.07
    قة
    -0.07
    _parse
    -0.07
    脑
    -0.07
     saç
    -0.06
     shards
    -0.06
    XA
    -0.06
     Annunci
    -0.06
     sóng
    -0.06
     cla
    -0.06
    POSITIVE LOGITS
    maximum
    0.07
     asks
    0.06
     italic
    0.06
     village
    0.06
     balloon
    0.06
     период
    0.06
     бюджет
    0.06
    usable
    0.06
    、↵↵
    0.06
     List
    0.06
    Act Density 0.001%

    No Known Activations