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

    Neuronpedia

    INDEX
    Explanations

    say punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flavor
    -0.07
     crem
    -0.07
     извест
    -0.07
    Um
    -0.07
    Wer
    -0.07
     Lexus
    -0.07
     edm
    -0.07
    商会
    -0.06
    疔
    -0.06
    情侣
    -0.06
    POSITIVE LOGITS
    對
    0.08
    IZES
    0.07
    更深
    0.07
     FETCH
    0.07
    既要
    0.07
     nearer
    0.07
    ط
    0.07
    present
    0.07
    把
    0.07
     rte
    0.06
    Act Density 0.006%

    No Known Activations