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

    Neuronpedia

    INDEX
    Explanations

    intr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     components
    -0.08
    inning
    -0.08
     engines
    -0.07
     groom
    -0.06
    .textBox
    -0.06
     bowls
    -0.06
    _two
    -0.06
     weapons
    -0.06
    мами
    -0.06
    _utils
    -0.06
    POSITIVE LOGITS
    喝
    0.07
     polov
    0.07
     الحرب
    0.06
    passwd
    0.06
    \Order
    0.06
    působ
    0.06
    anst
    0.06
    SingleOrDefault
    0.06
     currentUser
    0.06
     sexually
    0.06
    Act Density 0.009%

    No Known Activations