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

    Neuronpedia

    INDEX
    Explanations

    dimensions (height, width, diameter)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.57
    ۔
    0.54
    ς
    0.51
    ما
    0.49
     on
    0.49
    ך
    0.47
     estrogen
    0.46
    锟
    0.45
    i
    0.44
     an
    0.43
    POSITIVE LOGITS
    il
    0.64
    ir
    0.53
    ell
    0.47
     beho
    0.46
     fáb
    0.45
    at
    0.44
    im
    0.43
    elje
    0.43
    el
    0.42
    volle
    0.42
    Act Density 0.023%

    No Known Activations