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

    Neuronpedia

    INDEX
    Explanations

    Dates and references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    供水
    -0.08
    _idle
    -0.07
    _closed
    -0.07
     Mirror
    -0.07
     отз
    -0.07
    _sun
    -0.07
    挥手
    -0.07
    alarm
    -0.07
    .timeline
    -0.07
    _enqueue
    -0.07
    POSITIVE LOGITS
    [k
    0.07
    들은
    0.07
    𝗻
    0.07
    cken
    0.07
     году
    0.07
    ╞
    0.07
     tem
    0.07
     learn
    0.07
    stąpi
    0.06
    ucceeded
    0.06
    Act Density 0.095%

    No Known Activations