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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    탭
    -0.07
    outu
    -0.07
    🍞
    -0.07
     closeButton
    -0.07
    浙
    -0.07
     tog
    -0.07
     GLenum
    -0.07
    .toolStripMenuItem
    -0.07
     volunte
    -0.06
     REUTERS
    -0.06
    POSITIVE LOGITS
    检疫
    0.07
     max
    0.07
     Identified
    0.07
    oll
    0.06
    ounds
    0.06
    precated
    0.06
     Question
    0.06
     SEX
    0.06
    =<
    0.06
    (block
    0.06
    Act Density 0.100%

    No Known Activations