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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drivetrain
    -0.09
     विश्व
    -0.08
     oval
    -0.08
    (VAR
    -0.08
     cloth
    -0.08
     laminated
    -0.08
     spoilers
    -0.07
    Cable
    -0.07
    无遮挡
    -0.07
     magnets
    -0.07
    POSITIVE LOGITS
     Mell
    0.11
    moothing
    0.09
     Zel
    0.09
     librarian
    0.09
     starred
    0.08
     Episodes
    0.08
    429
    0.08
     Mozart
    0.08
     éto
    0.08
     zend
    0.08
    Act Density 0.006%

    No Known Activations