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

    Neuronpedia

    INDEX
    Explanations

    commas/quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𫓯
    -0.07
    功德
    -0.07
    באר
    -0.07
    ጽ
    -0.07
    뚠
    -0.06
    䐀
    -0.06
    -MM
    -0.06
     достиг
    -0.06
    变异
    -0.06
    .Xml
    -0.06
    POSITIVE LOGITS
     syst
    0.08
    assoc
    0.08
    WhiteSpace
    0.07
    “How
    0.07
    几年
    0.07
    _tags
    0.07
     Attacks
    0.07
    otty
    0.07
     Gen
    0.07
    	priv
    0.07
    Act Density 0.479%

    No Known Activations