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

    Neuronpedia

    INDEX
    Explanations

    Laundry instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Achievement
    -0.08
    λικά
    -0.08
    98
    -0.07
    vati
    -0.07
     homer
    -0.07
     Marshal
    -0.07
    niec
    -0.07
    97
    -0.07
    ेका
    -0.07
     Thi
    -0.07
    POSITIVE LOGITS
     рекомендуется
    0.10
     совет
    0.09
     recommend
    0.09
     recommends
    0.09
    は禁止
    0.09
    建议
    0.09
    rollers
    0.09
     aanbevolen
    0.08
     empfohlen
    0.08
     الأف
    0.08
    Act Density 0.008%

    No Known Activations