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

    Neuronpedia

    INDEX
    Explanations

    font-family: sans-serif

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    탈
    0.70
     фрон
    0.70
     တ
    0.70
    amples
    0.69
     Behind
    0.68
    눙
    0.68
     QnrB
    0.68
     Sales
    0.67
     মাইল
    0.66
     misa
    0.66
    POSITIVE LOGITS
     smoothly
    0.72
     ajust
    0.72
     smooth
    0.67
    耧
    0.66
     featured
    0.65
     smoother
    0.65
    smooth
    0.65
    smoothing
    0.64
    ead
    0.63
    ซีน
    0.63
    Act Density 0.002%

    No Known Activations