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

    Neuronpedia

    INDEX
    Explanations

    bracket "["

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chấp
    -0.07
     силы
    -0.06
    IPH
    -0.06
    kaz
    -0.06
    ngx
    -0.06
     노하우
    -0.06
     sürdür
    -0.06
     DAN
    -0.06
    .Board
    -0.06
     nhờ
    -0.06
    POSITIVE LOGITS
     trait
    0.07
    #[
    0.06
    crets
    0.06
    变
    0.06
     heavily
    0.06
    升
    0.06
    變
    0.06
     mechanisms
    0.06
    plots
    0.06
     Mae
    0.06
    Act Density 0.008%

    No Known Activations