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

    Neuronpedia

    INDEX
    Explanations

    lists, includes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ­t
    -0.07
    osopher
    -0.06
    yeah
    -0.06
    placer
    -0.06
     شک
    -0.06
    placed
    -0.06
     Porto
    -0.06
     awaits
    -0.06
    реж
    -0.06
     вне
    -0.05
    POSITIVE LOGITS
     exce
    0.07
     ประเทศ
    0.06
     fif
    0.06
    .mvc
    0.06
    ippets
    0.06
    aż
    0.06
     кли
    0.06
    attro
    0.06
     subtract
    0.06
    lep
    0.06
    Act Density 0.052%

    No Known Activations