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

    Neuronpedia

    INDEX
    Explanations

    Code variable types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovny
    -0.07
    振り
    -0.07
    esát
    -0.07
     імен
    -0.06
     ardından
    -0.06
     Sosyal
    -0.06
    wear
    -0.06
     bào
    -0.06
     thay
    -0.06
     wur
    -0.06
    POSITIVE LOGITS
    Bonjour
    0.06
    =int
    0.06
     introduce
    0.06
    .method
    0.06
    轻
    0.06
    　ノ
    0.06
    ,int
    0.06
    comm
    0.06
    ]()↵
    0.05
     flipping
    0.05
    Act Density 0.003%

    No Known Activations