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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     연결
    -0.06
     Zw
    -0.06
    izzlies
    -0.06
    ックス
    -0.06
    ð
    -0.06
     Predicate
    -0.06
    طة
    -0.06
    	cont
    -0.06
     Wak
    -0.06
     H
    -0.06
    POSITIVE LOGITS
    RATE
    0.07
    =${
    0.07
    NotExist
    0.07
     громадян
    0.06
     marathon
    0.06
    spath
    0.06
     آ
    0.06
     Meer
    0.06
     wear
    0.06
     Socorro
    0.06
    Act Density 0.001%

    No Known Activations