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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     merch
    -0.08
    _gender
    -0.08
    _opcode
    -0.08
     merchandise
    -0.07
    Province
    -0.07
    .deserialize
    -0.07
    .project
    -0.07
    _block
    -0.07
    zip
    -0.07
    Project
    -0.07
    POSITIVE LOGITS
     logarith
    0.12
     ordinate
    0.10
     ln
    0.10
     analytical
    0.09
     entropy
    0.08
     Abram
    0.08
     exponential
    0.08
    走势
    0.08
     Ln
    0.08
     hump
    0.08
    Act Density 0.087%

    No Known Activations