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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DataSet
    -0.07
     trium
    -0.07
    okedex
    -0.07
    -Mart
    -0.07
    PROGRAM
    -0.06
    high
    -0.06
     continu
    -0.06
     resorts
    -0.06
    apped
    -0.06
    izada
    -0.06
    POSITIVE LOGITS
    �
    0.07
     helm
    0.07
     inhabited
    0.06
     SK
    0.06
     Sabb
    0.06
     ním
    0.06
    .Service
    0.06
    _ble
    0.06
    .hl
    0.06
     mqtt
    0.06
    Act Density 0.070%

    No Known Activations