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

    Neuronpedia

    INDEX
    Explanations

    legal statutes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	synchronized
    -0.07
    isses
    -0.07
    -lnd
    -0.07
    achen
    -0.07
    씻
    -0.07
    实惠
    -0.07
    镄
    -0.07
    -s
    -0.07
    坼
    -0.06
    专
    -0.06
    POSITIVE LOGITS
     MODE
    0.07
     bal
    0.07
     głównie
    0.07
    (INT
    0.06
    CLUDING
    0.06
     stat
    0.06
    뭬
    0.06
     admir
    0.06
     قال
    0.06
    SENT
    0.06
    Act Density 0.035%

    No Known Activations