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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pedestal
    -0.08
    สูง
    -0.08
    ไฟ
    -0.08
     espalda
    -0.07
    _FL
    -0.07
     Kay
    -0.07
    .Final
    -0.07
     العالية
    -0.07
     narration
    -0.07
     boosters
    -0.07
    POSITIVE LOGITS
    集合
    0.13
    subset
    0.12
     subsets
    0.12
     subset
    0.11
     Sammlung
    0.11
     مجموعه
    0.11
     inhabited
    0.11
    名单
    0.10
    列表
    0.10
     seznam
    0.10
    Act Density 0.104%

    No Known Activations