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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summary
    -0.07
     considerable
    -0.07
     Mason
    -0.07
    ighborhood
    -0.07
    كي
    -0.07
     advertisement
    -0.07
     anonymous
    -0.07
    كت
    -0.07
    文章
    -0.06
    积
    -0.06
    POSITIVE LOGITS
    @Configuration
    0.06
    cstdint
    0.06
    UGH
    0.06
     saúde
    0.06
     Trend
    0.06
    urgeon
    0.05
    isex
    0.05
     оди
    0.05
     Yorkers
    0.05
    _Double
    0.05
    Act Density 0.020%

    No Known Activations