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
     collage
    -0.08
     EINA
    -0.07
     לעולם
    -0.07
     במסגרת
    -0.07
    🎭
    -0.07
    🎍
    -0.07
     Indonesian
    -0.07
     tah
    -0.07
    スタン
    -0.07
     génér
    -0.07
    POSITIVE LOGITS
    提到
    0.07
     stated
    0.07
    Found
    0.07
    到了
    0.07
    .Exception
    0.07
    满了
    0.07
    叙述
    0.06
    茬
    0.06
    Opened
    0.06
    Played
    0.06
    Act Density 0.178%

    No Known Activations