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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disappeared
    -0.07
    Print
    -0.07
    ｀ヽ
    -0.06
    <translation
    -0.06
     出
    -0.06
    iếm
    -0.06
     zpracování
    -0.06
    URLException
    -0.06
     schle
    -0.06
     twelve
    -0.06
    POSITIVE LOGITS
     factors
    0.12
     factor
    0.12
     Factors
    0.11
     Factor
    0.11
    Factors
    0.10
    Factor
    0.09
    factor
    0.09
     MAT
    0.09
     Jak
    0.08
    ifer
    0.08
    Act Density 0.032%

    No Known Activations