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

    Neuronpedia

    INDEX
    Explanations

    reverse order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    使用
    0.49
     […]
    0.48
     очи
    0.45
     Türk
    0.45
     неза
    0.44
     среди
    0.43
     ка
    0.42
     كأس
    0.42
     अॅ
    0.42
     центра
    0.41
    POSITIVE LOGITS
     hearted
    0.79
     didnt
    0.68
     terrible
    0.66
     doesnt
    0.65
     Trebuie
    0.65
     horrible
    0.64
     Thankfully
    0.63
     slightest
    0.63
     elves
    0.61
     Perhaps
    0.61
    Act Density 0.000%

    No Known Activations