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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XP
    -0.07
     למנ
    -0.07
    ҭ
    -0.07
     pq
    -0.07
     غزة
    -0.07
     Cortex
    -0.07
    สะสม
    -0.06
    .hardware
    -0.06
     Conway
    -0.06
    uint
    -0.06
    POSITIVE LOGITS
     preceded
    0.08
    рг
    0.08
    jem
    0.07
    专项行动
    0.07
    дать
    0.07
     dames
    0.07
    ISTS
    0.07
     pedals
    0.06
     channelId
    0.06
    _models
    0.06
    Act Density 0.001%

    No Known Activations