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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     degraded
    -0.06
    ,G
    -0.06
     zd
    -0.06
     rins
    -0.06
     radi
    -0.06
    .avi
    -0.06
    ,...↵
    -0.06
     ‪
    -0.06
     crimson
    -0.06
     downloadable
    -0.06
    POSITIVE LOGITS
    ском
    0.06
    iges
    0.06
     retrieve
    0.06
    .collection
    0.06
    善
    0.06
    Chapter
    0.06
    _rep
    0.06
    920
    0.06
     lure
    0.06
     constraint
    0.06
    Act Density 0.175%

    No Known Activations