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

    Neuronpedia

    INDEX
    Explanations

    Networking protocols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eclipse
    -0.07
     "/"↵
    -0.07
    bben
    -0.07
     Stephens
    -0.07
    スタ
    -0.07
     PURE
    -0.07
    ！”
    -0.07
    🇩
    -0.06
    renc
    -0.06
    грам
    -0.06
    POSITIVE LOGITS
    -processing
    0.07
     similarities
    0.07
    .pkl
    0.07
    _ll
    0.07
     (()
    0.07
     balls
    0.06
    团伙
    0.06
    .fin
    0.06
    orElse
    0.06
    okit
    0.06
    Act Density 0.019%

    No Known Activations