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

    Neuronpedia

    INDEX
    Explanations

    fractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     omgeving
    -0.08
     addiction
    -0.07
     Maar
    -0.07
     plek
    -0.07
     Klima
    -0.07
     partners
    -0.07
     கலந்து
    -0.07
     interactive
    -0.07
     partner
    -0.07
    .partner
    -0.07
    POSITIVE LOGITS
     numerator
    0.18
    )/(
    0.10
     denominator
    0.10
    -/
    0.09
     crimson
    0.09
     quince
    0.08
    umerator
    0.08
     Meanwhile
    0.08
    ))/(
    0.08
     Доб
    0.08
    Act Density 0.093%

    No Known Activations