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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Veteran
    -0.08
     averages
    -0.08
    Veter
    -0.07
     hyster
    -0.07
     Exper
    -0.07
     verr
    -0.07
     servant
    -0.07
     дистан
    -0.07
     introductory
    -0.07
     phenomenon
    -0.07
    POSITIVE LOGITS
     copro
    0.09
     decomposition
    0.09
     pollen
    0.09
    析
    0.08
     assembling
    0.08
     വിഭ
    0.08
    արս
    0.08
    igos
    0.08
     سبح
    0.08
     भाज
    0.08
    Act Density 0.031%

    No Known Activations