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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rod
    -0.07
     Rod
    -0.07
    _channel
    -0.06
     Jam
    -0.06
     lept
    -0.06
     coincide
    -0.06
    /tutorial
    -0.06
     ($("#
    -0.06
     исч
    -0.06
    cassert
    -0.06
    POSITIVE LOGITS
    lomou
    0.06
    /game
    0.06
    /man
    0.06
    aneously
    0.06
     इनक
    0.06
     перест
    0.06
     OST
    0.06
    거래
    0.06
     olay
    0.06
     Indones
    0.06
    Act Density 0.004%

    No Known Activations