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

    Neuronpedia

    INDEX
    Explanations

    explanation or instruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ОВА
    0.54
    ק
    0.50
    喪
    0.49
    ONO
    0.49
    ロッパ
    0.49
    畢
    0.48
    ิ
    0.46
     закона
    0.46
    ETO
    0.45
    複
    0.45
    POSITIVE LOGITS
     When
    0.56
     While
    0.55
     Thus
    0.54
     So
    0.53
     რაც
    0.52
     Now
    0.51
     Through
    0.51
    இதனால்
    0.51
     Hence
    0.50
     இதனால்
    0.50
    Act Density 0.002%

    No Known Activations