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

    Neuronpedia

    INDEX
    Explanations

    .Serializable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affirmation
    -0.07
    spi
    -0.07
    -flash
    -0.07
     Hale
    -0.07
     error
    -0.06
    /raw
    -0.06
    _sta
    -0.06
    铄
    -0.06
    lage
    -0.06
    聪
    -0.06
    POSITIVE LOGITS
     Gobierno
    0.07
     pornô
    0.07
    𫘬
    0.07
     integers
    0.07
    包含
    0.07
     ))↵
    0.07
    );\
    0.07
    短时间内
    0.07
    -fashioned
    0.07
    רכזי
    0.07
    Act Density 0.001%

    No Known Activations