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

    Neuronpedia

    INDEX
    Explanations

    Legal "relief" context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jíž
    -0.07
    guided
    -0.07
    Ether
    -0.07
    Pal
    -0.07
    _DEN
    -0.07
    >",↵
    -0.06
     cracking
    -0.06
    (Constants
    -0.06
     pudding
    -0.06
     Sharp
    -0.06
    POSITIVE LOGITS
    род
    0.07
    _notifier
    0.06
    мер
    0.06
    ouston
    0.06
     чолов
    0.06
    ยวข
    0.06
    veedor
    0.06
    .sound
    0.06
    llib
    0.06
    CHED
    0.06
    Act Density 0.017%

    No Known Activations