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

    Neuronpedia

    INDEX
    Explanations

    code, paths, symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opens
    -0.08
     ease
    -0.07
    只
    -0.07
     beauty
    -0.07
     DER
    -0.07
     Sanford
    -0.07
     次
    -0.07
    им
    -0.06
     thọ
    -0.06
     Brother
    -0.06
    POSITIVE LOGITS
     ประก
    0.06
     결
    0.06
    UserData
    0.06
    gui
    0.06
     prolet
    0.06
    บน
    0.06
    _typeDefinition
    0.06
     functools
    0.06
    .textColor
    0.05
     رب
    0.05
    Act Density 1.528%

    No Known Activations