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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flavors
    -0.08
    ית
    -0.08
     assure
    -0.08
     confirme
    -0.08
     meet
    -0.08
    Flavor
    -0.08
     несмотря
    -0.08
     hvorfor
    -0.07
    Despite
    -0.07
     הרש
    -0.07
    POSITIVE LOGITS
     polynomial
    0.09
     Polynomial
    0.08
    Polynomial
    0.08
    enius
    0.08
     polyval
    0.08
    _ylabel
    0.07
     sustit
    0.07
     VIC
    0.07
     childcare
    0.07
     मुकाब
    0.07
    Act Density 0.008%

    No Known Activations