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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    秃
    -0.07
    .TO
    -0.07
    招标
    -0.07
    MaxLength
    -0.07
    -[
    -0.07
    要加强
    -0.06
    提倡
    -0.06
    .Alter
    -0.06
     euro
    -0.06
     NRL
    -0.06
    POSITIVE LOGITS
     hiển
    0.08
     bek
    0.07
    נצי
    0.07
    azı
    0.07
    핱
    0.07
     سم
    0.07
     hazır
    0.06
     ayrıl
    0.06
     ביחד
    0.06
     dõi
    0.06
    Act Density 0.084%

    No Known Activations