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

    Neuronpedia

    INDEX
    Explanations

    approach to outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ключа
    0.46
     aromatic
    0.45
     anna
    0.43
     зазна
    0.43
     élim
    0.43
     arbor
    0.43
     ant
    0.43
     monastic
    0.42
    ధ
    0.42
     adel
    0.42
    POSITIVE LOGITS
    動き
    0.52
    睥
    0.50
     Biblioteca
    0.49
     京都
    0.49
    δί
    0.47
    fted
    0.47
     Chayin
    0.47
    <0xA3>
    0.46
    Lf
    0.46
    Vcs
    0.46
    Act Density 0.000%

    No Known Activations