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

    Neuronpedia

    INDEX
    Explanations

    Code/debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Salem
    -0.07
     LSTM
    -0.07
    _resume
    -0.06
    -designed
    -0.06
    Ali
    -0.06
     Warehouse
    -0.06
    .initialize
    -0.06
    .good
    -0.06
     Contains
    -0.06
    Administr
    -0.06
    POSITIVE LOGITS
    (light
    0.08
     ром
    0.07
     недел
    0.07
     ابراه
    0.07
    湿
    0.06
     shovel
    0.06
     BCH
    0.06
    iền
    0.06
     sợ
    0.06
    鼓
    0.06
    Act Density 0.046%

    No Known Activations