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

    Neuronpedia

    INDEX
    Explanations

    doctor will perform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एकेडमी
    0.43
    ala
    0.42
     Secretariat
    0.42
     الإلكتر
    0.41
     Perry
    0.41
    ਿਆਂ
    0.41
    franch
    0.40
     earmarked
    0.40
    िया
    0.40
     Iqbal
    0.40
    POSITIVE LOGITS
     Derived
    0.45
    excludes
    0.45
     tü
    0.44
    减少
    0.44
    leding
    0.44
     gdyż
    0.44
     derived
    0.43
     carcinogenic
    0.43
     根据
    0.42
     monos
    0.42
    Act Density 0.002%

    No Known Activations