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

    Neuronpedia

    INDEX
    Explanations

    programming code/libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOGGER
    -0.07
     bed
    -0.07
    大学生
    -0.07
    _LOGIN
    -0.06
    🍒
    -0.06
    BER
    -0.06
     succession
    -0.06
     אני
    -0.06
     sewer
    -0.06
    .ServiceModel
    -0.06
    POSITIVE LOGITS
    entin
    0.07
    hook
    0.07
     программы
    0.07
     Produk
    0.07
     imprimir
    0.07
     dó
    0.07
    (image
    0.07
    استعراض
    0.07
    msgs
    0.06
    entina
    0.06
    Act Density 0.146%

    No Known Activations