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

    Neuronpedia

    INDEX
    Explanations

    leading provider of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bessere
    0.61
     neuen
    0.60
    可通过
    0.59
     alcuni
    0.57
     aktuellen
    0.57
    ร
    0.57
    ne
    0.55
     těchto
    0.55
     einigen
    0.55
    {
    0.54
    POSITIVE LOGITS
     NASDAQ
    0.52
     проблемой
    0.50
    зад
    0.50
     trading
    0.49
     Trading
    0.49
    菸
    0.48
    마트
    0.48
     inégal
    0.48
    Trading
    0.47
    trading
    0.47
    Act Density 0.018%

    No Known Activations