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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cavalry
    -0.09
     redesigned
    -0.09
    -command
    -0.09
     steel
    -0.08
     landscaping
    -0.08
     redesign
    -0.08
     intimidation
    -0.08
     TRE
    -0.08
     sanitaires
    -0.08
    -General
    -0.08
    POSITIVE LOGITS
     fractional
    0.11
    Fraction
    0.09
     madrugada
    0.09
     Fraction
    0.09
     remainder
    0.09
    _fraction
    0.09
     accumulate
    0.08
     округ
    0.08
    _frac
    0.08
    rounded
    0.08
    Act Density 0.037%

    No Known Activations