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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tage
    -0.07
     sextreffen
    -0.06
     �
    -0.06
     tường
    -0.06
     heater
    -0.06
    _dynamic
    -0.06
     นาง
    -0.06
     тен
    -0.06
     اصفه
    -0.06
    兴
    -0.06
    POSITIVE LOGITS
    .tc
    0.07
     buck
    0.07
     determining
    0.07
     complimentary
    0.07
     Por
    0.07
    [ip
    0.07
    (bin
    0.07
     Boots
    0.07
    _sequence
    0.07
     require
    0.07
    Act Density 0.011%

    No Known Activations