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

    Neuronpedia

    INDEX
    Explanations

    words ending lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isotopes
    1.35
    Е
    1.13
     quadrant
    1.12
    َر
    1.11
     fungicides
    1.10
     solvents
    1.10
     insecticides
    1.10
    Х
    1.10
    Ш
    1.09
     oxides
    1.08
    POSITIVE LOGITS
    י
    1.17
    вання
    1.16
    cesis
    1.11
     відноси
    1.09
    zewski
    1.07
    க்குழு
    1.07
    ˩
    1.06
    と思います
    1.05
     mewah
    1.04
     sendiri
    1.01
    Act Density 0.001%

    No Known Activations