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

    Neuronpedia

    INDEX
    Explanations

    mechanical connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aris
    -0.07
    发布
    -0.07
    SO
    -0.07
     submit
    -0.07
     daher
    -0.06
     NA
    -0.06
     Rew
    -0.06
    (t
    -0.06
     asia
    -0.06
     testimon
    -0.06
    POSITIVE LOGITS
    артам
    0.07
    -к
    0.06
     ButterKnife
    0.06
    .cleanup
    0.06
    етерб
    0.06
     yapacak
    0.06
     muscular
    0.06
    (scale
    0.06
     şöyle
    0.06
    َال
    0.06
    Act Density 0.035%

    No Known Activations