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

    Neuronpedia

    INDEX
    Explanations

    frustration/player inconvenience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pump
    -0.07
    stration
    -0.07
    _https
    -0.07
     ACTION
    -0.07
    encil
    -0.07
    ThreadPool
    -0.07
     Known
    -0.06
     return
    -0.06
     closed
    -0.06
     action
    -0.06
    POSITIVE LOGITS
    六
    0.07
    ارش
    0.06
    寿
    0.06
    озем
    0.06
    tě
    0.06
    ()>↵
    0.06
     trấn
    0.06
    DMIN
    0.06
     för
    0.06
     �
    0.05
    Act Density 0.034%

    No Known Activations