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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     עיצוב
    -0.07
    这首歌
    -0.07
     battling
    -0.07
    瘋
    -0.07
    쩔
    -0.07
    庑
    -0.07
     anthem
    -0.07
    favicon
    -0.07
     <->
    -0.06
    .Helpers
    -0.06
    POSITIVE LOGITS
    (height
    0.09
    (Object
    0.07
    HeadersHeightSizeMode
    0.07
    _hor
    0.07
    ()<
    0.07
    -how
    0.07
    _high
    0.07
    ario
    0.07
     �
    0.07
    (tx
    0.07
    Act Density 0.014%

    No Known Activations