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

    Neuronpedia

    INDEX
    Explanations

    futures contracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хождения
    0.70
     internacionales
    0.66
     internacionais
    0.66
    𝓲
    0.65
    錯誤
    0.61
    рыва
    0.61
     bato
    0.61
    ин
    0.60
    ᅭ
    0.60
    фика
    0.60
    POSITIVE LOGITS
    vd
    0.56
    aff
    0.55
    aaa
    0.54
    op
    0.51
    ano
    0.51
    service
    0.51
    repo
    0.50
    ena
    0.50
    ۔
    0.50
    self
    0.49
    Act Density 0.006%

    No Known Activations