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

    Neuronpedia

    INDEX
    Explanations

    CRT, Bot, tipsters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    您可以
    2.10
    你可以
    1.99
     företag
    1.84
     Daryl
    1.81
     পাশাপাশি
    1.78
    ennial
    1.77
    そして
    1.74
     फ्रेंड्स
    1.73
     vistos
    1.71
    Believe
    1.70
    POSITIVE LOGITS
    фика
    1.75
    _{
    1.66
    _:
    1.64
    क
    1.63
    ter
    1.59
    mutable
    1.58
    人士
    1.54
    ^{
    1.53
    忑
    1.52
    دق
    1.51
    Act Density 0.000%

    No Known Activations