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

    Neuronpedia

    INDEX
    Explanations

    Code and testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    הז
    -0.08
    阶段
    -0.07
     fug
    -0.07
    有所
    -0.07
    不小心
    -0.07
    崡
    -0.07
    ں
    -0.06
    รวบ
    -0.06
    frau
    -0.06
    分別
    -0.06
    POSITIVE LOGITS
    Labels
    0.07
    .childNodes
    0.07
    <Book
    0.07
     Inter
    0.07
    棤
    0.07
    Crear
    0.07
     ptr
    0.07
     OPER
    0.07
     POSIX
    0.06
     escalating
    0.06
    Act Density 0.019%

    No Known Activations