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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Crud
    -0.07
    踹
    -0.07
    Brun
    -0.07
    -led
    -0.07
    Beth
    -0.07
     shouldBe
    -0.07
    Eb
    -0.07
     turned
    -0.07
     реша
    -0.06
    Limited
    -0.06
    POSITIVE LOGITS
    城区
    0.08
     Time
    0.07
    etrics
    0.07
    ኍ
    0.07
    文字
    0.07
    map
    0.07
    _representation
    0.07
     histories
    0.06
    .namespace
    0.06
    chars
    0.06
    Act Density 0.017%

    No Known Activations