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

    Neuronpedia

    INDEX
    Explanations

    circumstances of birth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кро
    0.80
    률
    0.80
    ตั้ง
    0.79
     सावधानी
    0.79
    իմ
    0.77
    局
    0.76
     Arten
    0.75
    zarchiwizowane
    0.75
     boyhood
    0.74
    ος
    0.74
    POSITIVE LOGITS
     into
    1.22
    out
    1.12
     tasmim
    0.93
     sull
    0.91
    アウト
    0.91
    𝕝
    0.90
     इनटू
    0.88
    avirus
    0.88
     onto
    0.87
     lysed
    0.87
    Act Density 0.003%

    No Known Activations