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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;|
    -0.07
    唯
    -0.06
     Noble
    -0.06
     Gavin
    -0.06
     semanas
    -0.06
     plains
    -0.06
    学校
    -0.06
     Bender
    -0.06
     vastly
    -0.06
    Viewport
    -0.06
    POSITIVE LOGITS
    identification
    0.07
     sexism
    0.06
    -cut
    0.06
     parody
    0.06
     dash
    0.06
    REC
    0.06
     android
    0.06
    TEST
    0.06
    _nf
    0.06
     Side
    0.06
    Act Density 0.002%

    No Known Activations