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

    Neuronpedia

    INDEX
    Explanations

    Discrimination, combines, mp4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eo
    3.31
    ei
    3.03
    y
    3.00
    aa
    2.84
    ्स
    2.82
    eau
    2.82
    ு
    2.76
    eat
    2.71
    eurs
    2.70
    yi
    2.69
    POSITIVE LOGITS
    ن
    2.54
    і
    2.20
    ש
    2.18
     simplicial
    2.07
    и
    2.06
    Ну
    1.90
    в
    1.88
    е
    1.87
    ang
    1.82
    на
    1.81
    Act Density 0.024%

    No Known Activations