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

    Neuronpedia

    INDEX
    Explanations

    contextual phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lacking
    0.47
     underwent
    0.46
     transnational
    0.43
     Blackberry
    0.42
     recounted
    0.42
     Tweets
    0.41
     retirees
    0.41
     undergone
    0.41
     recessed
    0.41
    ，
    0.41
    POSITIVE LOGITS
    த்தையும்
    0.58
    문의
    0.49
    odigd
    0.49
    prz
    0.48
    🔑
    0.48
    양
    0.48
    ሟ
    0.45
    이스
    0.45
    사용
    0.44
    сына
    0.44
    Act Density 0.006%

    No Known Activations