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

    Neuronpedia

    INDEX
    Explanations

    hair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ExceptionHandler
    -0.07
     方
    -0.06
    -deals
    -0.06
    Express
    -0.06
     OG
    -0.06
     får
    -0.06
    Clinton
    -0.06
    iales
    -0.06
    Extract
    -0.06
     Woj
    -0.06
    POSITIVE LOGITS
     hair
    0.07
     prize
    0.07
     Hair
    0.07
     sculpture
    0.07
     pokrač
    0.06
     reput
    0.06
     πολύ
    0.06
     poems
    0.06
    idores
    0.06
    ี้
    0.06
    Act Density 0.004%

    No Known Activations