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

    Neuronpedia

    INDEX
    Explanations

    Choose a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CHILD
    0.52
    是非常
    0.50
    可以看出
    0.48
    Ｔ
    0.47
     T
    0.46
     Château
    0.46
    非常
    0.45
     Antonia
    0.45
     adhered
    0.45
     rues
    0.45
    POSITIVE LOGITS
    en
    0.67
    ings
    0.67
     yourself
    0.63
     Yourself
    0.62
    ер
    0.59
    es
    0.58
    yourself
    0.58
    ers
    0.57
    ad
    0.55
    ığınız
    0.55
    Act Density 1.874%

    No Known Activations