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

    Neuronpedia

    INDEX
    Explanations

    Uttar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洒
    -0.07
     rulings
    -0.07
    啄
    -0.07
     FUN
    -0.07
     uy
    -0.07
     ['',
    -0.07
    —in
    -0.07
     ME
    -0.07
     Caf
    -0.07
     aracı
    -0.07
    POSITIVE LOGITS
    $d
    0.08
     água
    0.07
    穩定
    0.07
    ものです
    0.06
     Naruto
    0.06
    idata
    0.06
     продолжа
    0.06
    旿
    0.06
    삶
    0.06
    特朗普
    0.06
    Act Density 0.042%

    No Known Activations