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

    Neuronpedia

    INDEX
    Explanations

    indicating difficulty or levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ramírez
    0.46
     IOException
    0.44
    に行く
    0.43
    神経
    0.43
     giggle
    0.41
     thrill
    0.41
    バス
    0.41
    ตัน
    0.41
     microseconds
    0.41
    тео
    0.40
    POSITIVE LOGITS
     on
    0.56
    ä
    0.47
    rul
    0.46
    one
    0.46
     "
    0.45
    bere
    0.44
    rarea
    0.43
    it
    0.43
     elementi
    0.43
     (
    0.42
    Act Density 0.010%

    No Known Activations