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

    Neuronpedia

    INDEX
    Explanations

    sequences and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     considere
    0.46
     Mentre
    0.44
    ла
    0.41
     celé
    0.40
     Cependant
    0.40
     Leave
    0.39
     noemen
    0.39
     laissant
    0.39
     valeur
    0.38
     deje
    0.38
    POSITIVE LOGITS
    filters
    0.54
    沆
    0.50
    گیری
    0.49
     incentiv
    0.49
    کریاں
    0.48
    maps
    0.48
     filters
    0.48
    数百
    0.47
     CGM
    0.47
    گی
    0.47
    Act Density 0.001%

    No Known Activations