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

    Neuronpedia

    INDEX
    Explanations

    excerpts from reports/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    емые
    -0.07
    Russia
    -0.07
    _SUB
    -0.07
    ellites
    -0.07
    fdb
    -0.06
    ngr
    -0.06
    宝
    -0.06
    �
    -0.06
    ahlen
    -0.06
    bpp
    -0.06
    POSITIVE LOGITS
     failed
    0.06
     groupId
    0.06
     石
    0.06
    ousedown
    0.06
    _result
    0.06
     torch
    0.06
    shuffle
    0.06
     藤
    0.06
    doctrine
    0.06
     defStyle
    0.06
    Act Density 0.000%

    No Known Activations