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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    řízení
    0.39
     وغیرہ
    0.38
    BlockFit
    0.38
    Methylsulfanyl
    0.38
     शेफाली
    0.36
    鷳
    0.35
     እንደሚ
    0.34
    ওয়্যার
    0.34
    䀦
    0.34
     등
    0.33
    POSITIVE LOGITS
    jpg
    0.63
    5
    0.50
    png
    0.49
    pdf
    0.44
    txt
    0.43
    0
    0.42
    exe
    0.42
    docx
    0.41
    JPG
    0.41
     They
    0.40
    Act Density 0.079%

    No Known Activations