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

    Neuronpedia

    INDEX
    Explanations

    suggestions for writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulg
    -0.07
    贡献
    -0.07
    헅
    -0.07
     tủ
    -0.06
    Consulta
    -0.06
     diabetic
    -0.06
    图书
    -0.06
     président
    -0.06
    吸附
    -0.06
    ilm
    -0.06
    POSITIVE LOGITS
    /filter
    0.07
    .Length
    0.07
    ","#
    0.06
     fleeting
    0.06
    _metrics
    0.06
     herramient
    0.06
    sometimes
    0.06
    这对于
    0.06
    django
    0.06
    Ber
    0.06
    Act Density 0.013%

    No Known Activations