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

    Neuronpedia

    INDEX
    Explanations

    technical letters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अा
    0.47
     aiming
    0.47
     ​​
    0.45
     NOAA
    0.45
     IVF
    0.44
     challenging
    0.44
     स्पे
    0.43
     reigning
    0.43
    চূ
    0.42
     圆
    0.42
    POSITIVE LOGITS
     s
    0.86
     c
    0.72
     p
    0.71
     S
    0.64
     Clk
    0.64
     d
    0.62
     sd
    0.61
     ss
    0.59
    ｐ
    0.59
    idx
    0.59
    Act Density 0.545%

    No Known Activations