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

    Neuronpedia

    INDEX
    Explanations

    makeup removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rank
    -0.08
    essin
    -0.08
     brochure
    -0.08
    앞
    -0.07
     assumes
    -0.07
     ranking
    -0.07
    every
    -0.07
    virt
    -0.07
     grand
    -0.07
    zaal
    -0.07
    POSITIVE LOGITS
     удаления
    0.13
     إزالة
    0.12
     limpeza
    0.11
     제거
    0.11
     removing
    0.11
     verwijderen
    0.11
     remover
    0.11
     limpar
    0.10
    Removing
    0.10
    Removal
    0.10
    Act Density 0.015%

    No Known Activations