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

    Neuronpedia

    INDEX
    Explanations

    pepper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dir
    -0.06
    .Space
    -0.06
    َب
    -0.06
     прин
    -0.06
    _HAVE
    -0.06
    	go
    -0.06
    ratulations
    -0.06
    folios
    -0.06
     drastically
    -0.06
    中文字幕
    -0.06
    POSITIVE LOGITS
    恩
    0.06
    .answers
    0.06
     dining
    0.06
    驾
    0.06
     mildly
    0.06
     irrit
    0.06
     없음
    0.06
    重要
    0.06
    867
    0.06
     ev
    0.06
    Act Density 0.008%

    No Known Activations