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

    Neuronpedia

    INDEX
    Explanations

    embedded youtube videos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    íveis
    -0.08
     workforce
    -0.07
     MMM
    -0.07
    ################################
    -0.07
    %">↵
    -0.07
     stre
    -0.07
     faithfully
    -0.07
    ']},↵
    -0.06
    囱
    -0.06
    웻
    -0.06
    POSITIVE LOGITS
     cv
    0.07
     LABEL
    0.07
    "It
    0.07
     تق
    0.07
    物品
    0.07
    _encrypt
    0.06
    锦
    0.06
     financial
    0.06
    _arg
    0.06
     Characters
    0.06
    Act Density 0.006%

    No Known Activations