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

    Neuronpedia

    INDEX
    Explanations

    Legal documents/court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isize
    -0.07
     Ak
    -0.07
    샆
    -0.07
     Polar
    -0.07
     accusation
    -0.07
     maximize
    -0.07
     Eisen
    -0.07
     Parameter
    -0.07
     positions
    -0.07
    PyObject
    -0.06
    POSITIVE LOGITS
    𝔴
    0.08
    约
    0.07
    .loading
    0.07
     brink
    0.06
     Utils
    0.06
    кл
    0.06
    喤
    0.06
     brightness
    0.06
    멱
    0.06
    _ENC
    0.06
    Act Density 0.001%

    No Known Activations