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

    Neuronpedia

    INDEX
    Explanations

    first impressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    遽
    -0.08
    亲情
    -0.08
     jour
    -0.08
     donc
    -0.07
     Brent
    -0.07
    (dr
    -0.07
    caret
    -0.07
    .writeFileSync
    -0.07
    璎
    -0.07
     syncing
    -0.07
    POSITIVE LOGITS
     {}",
    0.07
    (program
    0.07
    帅
    0.06
    .rad
    0.06
     Bei
    0.06
    잠
    0.06
     black
    0.06
     Prefer
    0.06
    !");↵↵
    0.06
    睄
    0.06
    Act Density 0.037%

    No Known Activations