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

    Neuronpedia

    INDEX
    Explanations

    measurement steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    well
    0.45
    φαν
    0.45
    она
    0.44
    utani
    0.44
    alone
    0.43
    sit
    0.43
    ou
    0.42
     Elat
    0.42
    a
    0.42
    сные
    0.41
    POSITIVE LOGITS
     عمومی
    0.47
    牷
    0.45
     전
    0.43
     Scotland
    0.43
     باقی
    0.43
     순
    0.42
    قية
    0.42
     seduce
    0.41
     Boxing
    0.41
     유럽
    0.40
    Act Density 0.004%

    No Known Activations