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

    Neuronpedia

    INDEX
    Explanations

    Fate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    office
    -0.09
    緒
    -0.08
     Riding
    -0.07
     office
    -0.07
    host
    -0.07
    办公
    -0.07
     preference
    -0.07
     hydrox
    -0.07
     lurking
    -0.07
     multim
    -0.07
    POSITIVE LOGITS
     Cait
    0.09
     коэффици
    0.08
     Wiki
    0.08
     категор
    0.08
     ҳисоб
    0.08
    (Value
    0.08
     kategori
    0.08
     STRING
    0.08
     катег
    0.08
     ị
    0.08
    Act Density 0.000%

    No Known Activations