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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hect
    -0.07
    เหล
    -0.07
     baz
    -0.07
     zeal
    -0.07
    ane
    -0.06
     steady
    -0.06
     precinct
    -0.06
    ़ा
    -0.06
    -Z
    -0.06
    Θ
    -0.06
    POSITIVE LOGITS
    .annotations
    0.07
    ...</
    0.07
    紹介
    0.07
     نظامی
    0.07
    INST
    0.07
     anime
    0.06
     Hilton
    0.06
    (Container
    0.06
     понад
    0.06
    lux
    0.06
    Act Density 0.012%

    No Known Activations