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

    Neuronpedia

    INDEX
    Explanations

    translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     volunteering
    -0.07
     wor
    -0.07
    ears
    -0.07
    رت
    -0.06
     ад
    -0.06
     Por
    -0.06
     collect
    -0.06
    φ
    -0.06
     Hats
    -0.06
     Kr
    -0.06
    POSITIVE LOGITS
    (STD
    0.07
    Arthur
    0.07
     Enabled
    0.07
    (Class
    0.07
     موسیقی
    0.07
     niż
    0.07
     CONTRIBUTORS
    0.07
    りの
    0.07
    (interval
    0.07
    <Transaction
    0.06
    Act Density 0.002%

    No Known Activations