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

    Neuronpedia

    INDEX
    Explanations

    currency amounts and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     влияния
    0.52
    ിച്ച്
    0.51
     военной
    0.50
    鑊
    0.50
     perdón
    0.46
     effectuées
    0.46
    𝗷
    0.46
    ିକ
    0.46
     ಮಕ್ಕಳ
    0.46
     влияние
    0.45
    POSITIVE LOGITS
    .
    0.52
     The
    0.51
    aven
    0.50
     Type
    0.49
     Target
    0.48
    </
    0.47
     All
    0.47
     Sour
    0.46
     Rabb
    0.46
     $
    0.46
    Act Density 0.002%

    No Known Activations