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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oprah
    -0.08
     ته
    -0.08
     قدر
    -0.08
     altar
    -0.07
     Vector
    -0.07
     Bottom
    -0.07
     Affordable
    -0.07
     Target
    -0.07
     qualifier
    -0.07
     Sure
    -0.07
    POSITIVE LOGITS
     derivatives
    0.09
    -derived
    0.09
     Leistung
    0.09
    Derivative
    0.08
     derivative
    0.08
    cretion
    0.08
    _der
    0.08
    :hover
    0.08
     производ
    0.08
    .locals
    0.08
    Act Density 0.023%

    No Known Activations