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

    Neuronpedia

    INDEX
    Explanations

    Internet forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _verify
    -0.07
    Pocket
    -0.06
    green
    -0.06
    dling
    -0.06
    -go
    -0.06
     연
    -0.06
    illos
    -0.06
     tenemos
    -0.06
    FE
    -0.06
     reduces
    -0.06
    POSITIVE LOGITS
     Європ
    0.07
     approximate
    0.06
     Brill
    0.06
     dynam
    0.06
    .ย
    0.06
     maur
    0.06
    تمع
    0.06
    Ả
    0.06
     {}
    0.06
     hvě
    0.06
    Act Density 0.003%

    No Known Activations