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

    Neuronpedia

    INDEX
    Explanations

    See how?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jelder
    0.41
     extol
    0.41
    discuss
    0.40
    leau
    0.40
    癜
    0.40
     Schall
    0.40
     Liebe
    0.38
    prf
    0.38
    itié
    0.38
    zechos
    0.38
    POSITIVE LOGITS
     simplicity
    0.50
    完成了
    0.47
     simpl
    0.45
    រួ
    0.42
     Completed
    0.42
    最初に
    0.42
    完成后
    0.41
    最後に
    0.41
     Finished
    0.39
     sencilla
    0.39
    Act Density 0.008%

    No Known Activations