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

    Neuronpedia

    INDEX
    Explanations

    Downloadable academic documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    עם
    -0.07
    #__
    -0.07
    ዝ
    -0.07
    숫
    -0.07
    FolderPath
    -0.07
     csvfile
    -0.07
    Accordion
    -0.07
     frequ
    -0.07
    quis
    -0.07
    .LogError
    -0.07
    POSITIVE LOGITS
    _CHILD
    0.08
    逸
    0.07
    LB
    0.07
     signing
    0.07
    child
    0.07
    UDENT
    0.06
     Airport
    0.06
    /'↵↵
    0.06
    	explicit
    0.06
    鞭
    0.06
    Act Density 0.039%

    No Known Activations