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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reconsider
    -0.07
    agate
    -0.07
     {*}
    -0.07
    danger
    -0.07
     Allocate
    -0.07
     handleError
    -0.07
    汽车产业
    -0.06
    .AnchorStyles
    -0.06
    眄
    -0.06
    odd
    -0.06
    POSITIVE LOGITS
    ﲨ
    0.08
    Ƴ
    0.07
    욺
    0.06
    이라는
    0.06
    <Text
    0.06
     YT
    0.06
    라는
    0.06
    这几
    0.06
     M
    0.06
    潵
    0.06
    Act Density 0.008%

    No Known Activations