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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -leaning
    -0.07
     Sam
    -0.06
     Λ
    -0.06
    Auto
    -0.06
     Crazy
    -0.06
     ベ
    -0.06
    planet
    -0.06
     Ragnar
    -0.06
     ΠΡ
    -0.06
    _Default
    -0.06
    POSITIVE LOGITS
    оже
    0.07
    ":{↵
    0.06
     осіб
    0.06
    타
    0.06
    (dl
    0.06
    urga
    0.06
    .fastjson
    0.06
    ovol
    0.06
    *,
    0.06
     왜
    0.06
    Act Density 0.002%

    No Known Activations