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

    Neuronpedia

    INDEX
    Explanations

    PLA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defendants
    -0.07
     boundaries
    -0.06
     incorporate
    -0.06
    (Settings
    -0.06
     Merge
    -0.06
    他的
    -0.06
     classify
    -0.06
    金额
    -0.06
     fuzzy
    -0.06
     coordinates
    -0.06
    POSITIVE LOGITS
    486
    0.07
    Tumblr
    0.07
     USE
    0.07
     مف
    0.06
    Pragma
    0.06
    /social
    0.06
     العملية
    0.06
    .IsSuccess
    0.06
    plugin
    0.06
    .'<
    0.06
    Act Density 0.001%

    No Known Activations