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

    Neuronpedia

    INDEX
    Explanations

    explicit sexual content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Intersection
    -0.07
     metabolic
    -0.07
    (Address
    -0.06
     Bios
    -0.06
    汇
    -0.06
     RU
    -0.06
     Nas
    -0.06
    prefix
    -0.06
    _item
    -0.06
     гриб
    -0.06
    POSITIVE LOGITS
    ॰
    0.06
    riv
    0.06
     TEntity
    0.06
     всего
    0.06
     undertaken
    0.06
    ตาม
    0.06
    [top
    0.06
     ctor
    0.06
    exercise
    0.06
    สด
    0.06
    Act Density 0.026%

    No Known Activations