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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idental
    -0.07
     pregunta
    -0.07
    morph
    -0.07
    holiday
    -0.07
    NSSet
    -0.07
     homosex
    -0.07
     nouns
    -0.07
     scenario
    -0.07
    clip
    -0.07
    mark
    -0.06
    POSITIVE LOGITS
     UAV
    0.07
    交易平台
    0.07
     Laboratories
    0.07
    CString
    0.07
    :\"
    0.07
     ...)
    0.07
     ePub
    0.07
    🕊
    0.07
    .configuration
    0.07
    	BYTE
    0.06
    Act Density 0.011%

    No Known Activations