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

    Neuronpedia

    INDEX
    Explanations

    amount and degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nunca
    0.42
    odhya
    0.41
     очень
    0.41
     невозможно
    0.41
    não
    0.41
     không
    0.40
     kleinere
    0.39
     Nunca
    0.39
    说什么
    0.38
    țit
    0.38
    POSITIVE LOGITS
     amount
    0.58
     extent
    0.57
     versus
    0.56
    程度
    0.54
     vs
    0.53
     degree
    0.50
    versus
    0.50
     কতটা
    0.50
    amount
    0.49
     насколько
    0.49
    Act Density 0.270%

    No Known Activations