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

    Neuronpedia

    INDEX
    Explanations

    or, not, by, then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isomorphism
    0.43
     現
    0.42
     डों
    0.41
    permut
    0.41
    Dimensional
    0.40
    AppBsky
    0.40
    पु
    0.39
    ódio
    0.39
     Sanz
    0.38
    ню
    0.38
    POSITIVE LOGITS
     surgeons
    0.52
     petrol
    0.48
    继续
    0.47
    每个
    0.46
    是一种
    0.45
     petroleum
    0.45
    一种
    0.44
     stranded
    0.44
     foodstuffs
    0.43
     shrunk
    0.43
    Act Density 0.001%

    No Known Activations