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

    Neuronpedia

    INDEX
    Explanations

    Water crossings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EQUAL
    -0.07
    رب
    -0.06
     Merrill
    -0.06
    (piece
    -0.06
    чих
    -0.06
    (tc
    -0.06
     cartridges
    -0.06
    .LE
    -0.06
    :Event
    -0.06
    公開
    -0.06
    POSITIVE LOGITS
    _sm
    0.07
    SY
    0.07
     รวม
    0.07
     NEC
    0.06
     formatter
    0.06
     ammonia
    0.06
    окрем
    0.06
     Simple
    0.06
     midnight
    0.06
     assault
    0.06
    Act Density 0.135%

    No Known Activations