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

    Neuronpedia

    INDEX
    Explanations

    technical assessments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鹚
    -0.08
    chsel
    -0.08
    .hom
    -0.07
    好き
    -0.07
    نتشر
    -0.07
    .None
    -0.07
    .ForEach
    -0.07
    三农
    -0.07
    بقاء
    -0.07
    Ẫ
    -0.07
    POSITIVE LOGITS
     calming
    0.07
    _successful
    0.07
     ↵	↵
    0.07
     calculated
    0.07
    ":[{↵
    0.07
    费率
    0.07
    )))));
↵
    0.07
     biblical
    0.06
     calories
    0.06
    谋
    0.06
    Act Density 0.024%

    No Known Activations