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

    Neuronpedia

    INDEX
    Explanations

    creating content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coli
    0.42
     statue
    0.41
    posX
    0.41
    coeff
    0.41
    num
    0.40
    ui
    0.40
    agent
    0.40
    mathop
    0.40
    imo
    0.40
    sterdam
    0.39
    POSITIVE LOGITS
     비율
    0.51
    ோ
    0.44
    0.44
    ொ
    0.42
     нә
    0.42
    뷰
    0.40
     అన
    0.40
     වූ
    0.39
     బాగా
    0.39
     బ్లా
    0.39
    Act Density 0.005%

    No Known Activations