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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WTF
    -0.07
    رب
    -0.06
    .owl
    -0.06
    ९
    -0.06
     condemnation
    -0.06
     Paging
    -0.06
    atar
    -0.06
    арч
    -0.06
    sexy
    -0.06
     Soup
    -0.05
    POSITIVE LOGITS
    ---
↵
    0.07
    iseum
    0.06
    lage
    0.06
    alue
    0.06
     și
    0.06
     ()↵
    0.06
     deletes
    0.06
     suggests
    0.06
     từng
    0.06
    ,strlen
    0.06
    Act Density 0.033%

    No Known Activations