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

    Neuronpedia

    INDEX
    Explanations

    programming utilities and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     téléphone
    0.67
     минуты
    0.67
    4
    0.64
     различные
    0.61
     není
    0.61
    ResBuffer
    0.60
     vuttam
    0.59
     této
    0.59
    ᚑ
    0.59
     phút
    0.59
    POSITIVE LOGITS
    in
    1.02
     in
    0.83
    g
    0.78
    world
    0.73
    t
    0.73
    evich
    0.69
    sell
    0.68
    p
    0.68
    is
    0.66
    land
    0.66
    Act Density 0.000%

    No Known Activations