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

    Neuronpedia

    INDEX
    Explanations

    Washing/laundry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     수행
    -0.07
     Advis
    -0.06
    ographical
    -0.06
    考核
    -0.06
    icycle
    -0.06
     indic
    -0.06
     excuse
    -0.06
    ḍ
    -0.06
     judgment
    -0.06
    门外
    -0.06
    POSITIVE LOGITS
     Overwatch
    0.09
     CGRect
    0.08
     hardness
    0.08
    Μ
    0.08
     tecnología
    0.08
    Roboto
    0.07
     bure
    0.07
     pretrained
    0.07
    苒
    0.07
     стол
    0.07
    Act Density 0.031%

    No Known Activations