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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gui
    -0.07
    PLAIN
    -0.07
     reinforcing
    -0.07
     upon
    -0.07
     optics
    -0.06
    asting
    -0.06
     onboard
    -0.06
     صورت
    -0.06
    ukan
    -0.06
     خوب
    -0.06
    POSITIVE LOGITS
    dbname
    0.11
     dbname
    0.09
     Eat
    0.06
    мами
    0.06
    _Category
    0.06
    Socket
    0.06
    _NEAR
    0.06
     Nim
    0.06
    -Man
    0.06
    _complete
    0.06
    Act Density 0.007%

    No Known Activations