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

    Neuronpedia

    INDEX
    Explanations

    the core logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     implementations
    0.88
    IOException
    0.79
    调用
    0.78
    接口
    0.77
    初始化
    0.75
     DEBUG
    0.75
    导入
    0.74
    াদা
    0.73
     debugging
    0.72
     Exceptions
    0.72
    POSITIVE LOGITS
     bombshell
    1.00
     ingenious
    0.98
     cynical
    0.98
     clever
    0.97
     innovative
    0.91
     expresión
    0.91
     выражение
    0.90
    innovation
    0.90
    উৎ
    0.88
     sneaky
    0.87
    Act Density 0.468%

    No Known Activations