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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    湯
    -0.06
     aktar
    -0.06
    olated
    -0.06
    ias
    -0.06
     quan
    -0.06
     flo
    -0.06
    Fx
    -0.06
    _orient
    -0.06
    咨
    -0.06
    _apps
    -0.06
    POSITIVE LOGITS
     Macron
    0.07
    thumbs
    0.06
    Simple
    0.06
     تسم
    0.06
    modes
    0.06
     nor
    0.06
     Son
    0.06
     brasile
    0.06
    ([],
    0.06
     Ж
    0.06
    Act Density 0.006%

    No Known Activations