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

    Neuronpedia

    INDEX
    Explanations

    past and continuing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.52
    ADA
    0.49
    (
    0.49
    Tasks
    0.48
    ↵↵
    0.45
    perature
    0.45
     ташки
    0.45
    upo
    0.43
    นั้น
    0.42
    verage
    0.42
    POSITIVE LOGITS
     chopsticks
    0.48
    št
    0.47
     இவர்
    0.45
     metres
    0.44
     visión
    0.44
     theseKeys
    0.44
     வள்ளி
    0.43
     இந்ந
    0.42
    ᆫ
    0.42
     mètres
    0.42
    Act Density 0.000%

    No Known Activations