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

    Neuronpedia

    INDEX
    Explanations

    type ofnature of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hurled
    0.68
     apunt
    0.65
     undone
    0.65
    _{\
    0.65
    _{
    0.63
     bood
    0.63
     vou
    0.61
    今日
    0.61
     vuelta
    0.61
    蜍
    0.61
    POSITIVE LOGITS
    LO
    0.80
    ﻑ
    0.79
    ve
    0.78
    𝒑
    0.75
    ಯೇ
    0.72
    ت
    0.72
    లోనే
    0.71
    یف
    0.70
    icine
    0.70
    ugeot
    0.68
    Act Density 0.546%

    No Known Activations