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

    Neuronpedia

    INDEX
    Explanations

    dragon, crystals, rates, your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పో
    0.53
    ート
    0.52
     روی
    0.50
     פור
    0.50
    ıyla
    0.49
     инструмент
    0.48
    ッケージ
    0.48
     ઉપયોગ
    0.47
     три
    0.46
     cara
    0.46
    POSITIVE LOGITS
    เดิม
    0.47
    och
    0.46
     एबी
    0.45
    renaline
    0.44
    esthetic
    0.43
    ppb
    0.43
     convictions
    0.43
    ᠯ
    0.41
    PAC
    0.41
    abang
    0.41
    Act Density 0.000%

    No Known Activations