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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itures
    -0.07
     pauses
    -0.07
    好的
    -0.07
    hud
    -0.06
    Caps
    -0.06
    OURCES
    -0.06
    有点
    -0.06
     흐
    -0.06
    ектора
    -0.06
     headphone
    -0.06
    POSITIVE LOGITS
    вед
    0.07
     isbn
    0.06
     dye
    0.06
    ublice
    0.06
     Анд
    0.06
    =open
    0.06
     çıkar
    0.06
    *_
    0.06
     grass
    0.06
     blonde
    0.06
    Act Density 0.311%

    No Known Activations