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

    Neuronpedia

    INDEX
    Explanations

    Generating code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erstwhile
    0.43
     कॅम्प
    0.42
     असंख्य
    0.42
     vielfält
    0.41
     여러분
    0.40
     Porque
    0.39
     jusqu
    0.39
     속에
    0.39
     BECAUSE
    0.39
     categoría
    0.39
    POSITIVE LOGITS
    Get
    0.77
    获取
    0.75
    get
    0.74
    update
    0.68
    calculate
    0.68
    处理
    0.67
    初始化
    0.66
     Get
    0.66
     get
    0.64
    prepare
    0.64
    Act Density 0.913%

    No Known Activations