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

    Neuronpedia

    INDEX
    Explanations

    sunny-side up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.45
    ed
    0.43
    i
    0.41
    ()];
    0.40
    request
    0.39
     PSU
    0.38
     jeho
    0.38
    portable
    0.38
     Instal
    0.38
    桩
    0.37
    POSITIVE LOGITS
     Appalach
    0.43
    ۔
    0.43
     geranium
    0.43
     உற
    0.43
     Aspen
    0.42
    ).
    0.42
    няют
    0.41
     कधी
    0.41
    XYGEN
    0.41
     Audubon
    0.41
    Act Density 0.002%

    No Known Activations