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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    戒
    -0.09
    _shutdown
    -0.07
    🍶
    -0.07
     شب
    -0.07
     Mü
    -0.07
    _DIS
    -0.07
     Państwo
    -0.07
    .xhtml
    -0.07
    桌
    -0.07
    .Network
    -0.07
    POSITIVE LOGITS
    illisecond
    0.08
    :relative
    0.07
    流淌
    0.06
     Lazar
    0.06
     LIKE
    0.06
    >(),↵
    0.06
    RAY
    0.06
    帮他
    0.06
    urgy
    0.06
     אית
    0.06
    Act Density 0.042%

    No Known Activations