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

    Neuronpedia

    INDEX
    Explanations

    Swinging/direction/extremes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detention
    -0.07
    交易中心
    -0.07
     😀
    -0.07
    .IsNullOrWhiteSpace
    -0.07
     mantra
    -0.07
    Conta
    -0.07
     bool
    -0.06
    赌
    -0.06
    oday
    -0.06
     Observatory
    -0.06
    POSITIVE LOGITS
     lys
    0.06
    arms
    0.06
    mic
    0.06
     Aff
    0.06
     sais
    0.06
    셜
    0.06
    kreśl
    0.06
    暗暗
    0.06
     ничего
    0.06
    .Escape
    0.06
    Act Density 0.056%

    No Known Activations