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

    Neuronpedia

    INDEX
    Explanations

    promoting respectful beneficial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ประมาณ
    0.47
    FindBy
    0.46
     maturities
    0.46
     rupani
    0.46
     hiệu
    0.45
     effectual
    0.44
    첸
    0.44
     thisobject
    0.44
     osią
    0.44
    िफाई
    0.43
    POSITIVE LOGITS
     Slack
    0.55
     Docker
    0.47
    ’
    0.46
    Reg
    0.45
     YouTube
    0.42
     v
    0.42
    Y
    0.42
     Lac
    0.42
     Ke
    0.41
     Rate
    0.41
    Act Density 0.001%

    No Known Activations