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

    Neuronpedia

    INDEX
    Explanations

    Skills, methods, and practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    目安
    0.36
    迅
    0.36
     ప్రభుత్వ
    0.36
    SegmentInfo
    0.36
    Authority
    0.36
     แนว
    0.36
    Lyrics
    0.36
    Dictionary
    0.35
    Discord
    0.35
    太
    0.35
    POSITIVE LOGITS
     practices
    0.50
     Practices
    0.44
     tangan
    0.44
     techniques
    0.44
     investigative
    0.44
     Verfahren
    0.44
     procedures
    0.43
     scraping
    0.43
     pratiquer
    0.43
     honed
    0.42
    Act Density 0.001%

    No Known Activations