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

    Neuronpedia

    INDEX
    Explanations

    memo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⾛
    -0.09
    既能
    -0.08
     ste
    -0.07
     времен
    -0.07
     Thời
    -0.07
     Taste
    -0.07
    existence
    -0.07
     dissolve
    -0.07
    精
    -0.07
    _TAGS
    -0.06
    POSITIVE LOGITS
    $pdf
    0.08
     aur
    0.07
    ดร
    0.07
    👉
    0.07
    SetTitle
    0.07
     üzere
    0.07
    ボール
    0.07
     самым
    0.07
    abant
    0.07
    apatkan
    0.07
    Act Density 0.004%

    No Known Activations