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

    Neuronpedia

    INDEX
    Explanations

    strike deep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ارت
    0.86
    センス
    0.76
    ಯೇ
    0.74
     Produkten
    0.73
     BVHTree
    0.73
    ઈ
    0.73
     Grossman
    0.71
     ಇದೆ
    0.70
     stockno
    0.70
    ourent
    0.70
    POSITIVE LOGITS
    ’
    0.90
     salvo
    0.79
     reliably
    0.76
    '
    0.75
    ws
    0.66
     hatch
    0.64
    regardless
    0.64
     subordinate
    0.63
     magically
    0.61
     securely
    0.60
    Act Density 0.001%

    No Known Activations