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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     группа
    -0.07
    GROUP
    -0.07
    ptype
    -0.07
    (Call
    -0.07
    (big
    -0.07
    .Document
    -0.07
    重度
    -0.07
    ован
    -0.07
    (ln
    -0.07
    (validate
    -0.07
    POSITIVE LOGITS
     Ap
    0.07
    糖
    0.07
    喝
    0.07
     plunder
    0.07
     المر
    0.07
    Decode
    0.07
    _FLASH
    0.07
    rip
    0.07
     panor
    0.07
     الإير
    0.07
    Act Density 0.042%

    No Known Activations