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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     June
    -0.08
    ซ
    -0.07
    .reader
    -0.07
     interes
    -0.07
     prisoner
    -0.07
     контрол
    -0.07
    Images
    -0.07
     unfamiliar
    -0.07
    瑕疵
    -0.07
     혹은
    -0.06
    POSITIVE LOGITS
    쟙
    0.08
    сты
    0.07
     stil
    0.07
    _CRITICAL
    0.07
    otonin
    0.07
    祓
    0.07
    <Block
    0.07
    风湿
    0.06
     Vapor
    0.06
     Drill
    0.06
    Act Density 0.014%

    No Known Activations