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

    Neuronpedia

    INDEX
    Explanations

    Kim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ѹ
    -0.08
     ()=>{↵
    -0.08
    有一个
    -0.08
    			
↵			
↵
    -0.07
    -placement
    -0.07
     honesty
    -0.07
    .j
    -0.07
    (Byte
    -0.07
    眼光
    -0.07
    ))];↵
    -0.07
    POSITIVE LOGITS
     Kim
    0.08
    ToList
    0.07
    _Rem
    0.07
    _INSERT
    0.07
    女孩子
    0.06
     defects
    0.06
    	Code
    0.06
    fm
    0.06
    朕
    0.06
    まとめ
    0.06
    Act Density 0.003%

    No Known Activations