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

    Neuronpedia

    INDEX
    Explanations

    code or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    婿
    0.48
    舉辦
    0.45
     ľudí
    0.45
     PNC
    0.43
    多家
    0.42
     décès
    0.42
    器官
    0.41
     людей
    0.41
     classement
    0.40
    เสียง
    0.40
    POSITIVE LOGITS
     script
    1.02
     scripts
    0.93
    script
    0.90
    代码
    0.89
    Script
    0.88
     code
    0.84
    脚本
    0.84
     scripting
    0.83
     Scripts
    0.82
     Script
    0.76
    Act Density 0.391%

    No Known Activations