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

    Neuronpedia

    INDEX
    Explanations

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pragmatic
    0.58
     perpetrators
    0.56
     mental
    0.56
     SMEs
    0.56
     Augen
    0.55
     คุณ
    0.55
     perennial
    0.54
     정신
    0.53
     physi
    0.52
     Renaissance
    0.52
    POSITIVE LOGITS
    初始化
    0.91
    调用
    0.91
     初始化
    0.89
    获取
    0.85
    遍历
    0.84
    读取
    0.83
     指定
    0.78
    删除
    0.76
    返回
    0.75
    当前
    0.75
    Act Density 1.391%

    No Known Activations