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

    Neuronpedia

    INDEX
    Explanations

    Code related to web development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .react
    -0.07
    ipelines
    -0.06
     classical
    -0.06
     Brah
    -0.06
    ropsych
    -0.06
     sau
    -0.06
    如有侵权
    -0.06
    _decay
    -0.06
    lds
    -0.06
    ología
    -0.06
    POSITIVE LOGITS
    面条
    0.07
     nivel
    0.07
     тек
    0.07
    ║
    0.07
     commend
    0.07
     jog
    0.07
    ***/↵
    0.06
    .Table
    0.06
    Size
    0.06
    钔
    0.06
    Act Density 0.008%

    No Known Activations