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

    Neuronpedia

    INDEX
    Explanations

    as e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ………………………………..
    0.45
     Durchmesser
    0.43
    䊂
    0.42
    乆
    0.41
    ➖➖
    0.41
     Autres
    0.41
    плення
    0.40
    宄
    0.40
     استعمال
    0.40
    mobilpay
    0.40
    POSITIVE LOGITS
     e
    0.74
     i
    0.70
     p
    0.65
     _
    0.63
    x
    0.63
     x
    0.62
     v
    0.60
     o
    0.59
    _
    0.59
     q
    0.56
    Act Density 0.032%

    No Known Activations