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

    Neuronpedia

    INDEX
    Explanations

    meet and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zony
    1.28
    ния
    1.05
    ടുത്ത
    1.04
    нить
    1.04
    ished
    1.04
     sırada
    1.02
     manifold
    1.02
    stash
    1.01
    蟲
    0.98
    schnitt
    0.97
    POSITIVE LOGITS
     adjourned
    1.54
    ronidazole
    1.37
    rical
    1.35
    atars
    1.28
     जुल
    1.25
    ups
    1.20
    徽
    1.18
    ropolitan
    1.17
    ので
    1.16
    oprol
    1.16
    Act Density 0.054%

    No Known Activations