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

    Neuronpedia

    INDEX
    Explanations

    philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denominator
    -0.09
    Nun
    -0.08
    Index
    -0.08
    -0.08
    Pivot
    -0.08
     क्यों
    -0.08
     recalled
    -0.08
     piv
    -0.07
    Po
    -0.07
     pribadi
    -0.07
    POSITIVE LOGITS
     বিজ্ঞান
    0.09
     científico
    0.09
     वैज्ञानिक
    0.09
     científicos
    0.09
    _cor
    0.08
     scientific
    0.08
     Scientific
    0.08
     science
    0.08
     cient
    0.08
    科学
    0.08
    Act Density 0.011%
    No Known Activations