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

    Neuronpedia

    INDEX
    Explanations

    timeout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    长安
    -0.07
    made
    -0.07
     Fot
    -0.07
    _ARM
    -0.07
     Turn
    -0.07
     sells
    -0.07
    reads
    -0.07
    /jav
    -0.07
     Dortmund
    -0.07
     independent
    -0.07
    POSITIVE LOGITS
    園
    0.07
    brush
    0.07
    空气
    0.06
    鲡
    0.06
    Timer
    0.06
    白
    0.06
    0.06
    arks
    0.06
    も多く
    0.06
    不平衡
    0.06
    Act Density 0.004%

    No Known Activations