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

    Neuronpedia

    INDEX
    Explanations

    document formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oric
    -0.07
     laptop
    -0.07
    是一
    -0.07
    َك
    -0.07
    ucle
    -0.07
    ُل
    -0.07
    浴
    -0.06
     答
    -0.06
    请选择
    -0.06
     pus
    -0.06
    POSITIVE LOGITS
     headings
    0.08
     Professor
    0.07
     Constructors
    0.06
    .unwrap
    0.06
     Hunts
    0.06
    .symmetric
    0.06
     Marathon
    0.06
     [--
    0.06
     Dyn
    0.06
    .functions
    0.06
    Act Density 0.011%

    No Known Activations