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

    Neuronpedia

    INDEX
    Explanations

    theme

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gpu
    -0.08
    ulner
    -0.07
    merge
    -0.07
    likely
    -0.07
    teil
    -0.07
    mouseleave
    -0.07
     femin
    -0.07
    十佳
    -0.07
    .verbose
    -0.07
     simult
    -0.06
    POSITIVE LOGITS
    Ст
    0.08
    有点
    0.07
     podía
    0.06
    联通
    0.06
     carbs
    0.06
     wrapper
    0.06
    MT
    0.06
    接口
    0.06
    .SelectedValue
    0.06
    なんだ
    0.06
    Act Density 0.003%

    No Known Activations