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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ребенка
    -0.07
     случаев
    -0.07
     �
    -0.07
    -inline
    -0.07
     forecasts
    -0.07
     latter
    -0.07
     Woodward
    -0.07
     с
    -0.07
     uplift
    -0.07
    se
    -0.07
    POSITIVE LOGITS
    (dto
    0.07
    zim
    0.06
    )\<
    0.06
    업체
    0.06
     또
    0.05
     menjadi
    0.05
     etmek
    0.05
     Verd
    0.05
    ()?>
    0.05
    yect
    0.05
    Act Density 0.042%

    No Known Activations