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

    Neuronpedia

    INDEX
    Explanations

    DNA transcription and assembly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stressors
    0.38
    ете
    0.34
    ج
    0.34
    ز
    0.32
     machine
    0.32
     participation
    0.31
     misc
    0.31
     storage
    0.31
    ્રે
    0.31
    قة
    0.30
    POSITIVE LOGITS
    votes
    0.39
    three
    0.38
     ಸುಮ
    0.38
    駙
    0.37
     ಕಾಂಗ್ರೆ
    0.37
    moires
    0.36
     восем
    0.36
     स्वर्ग
    0.36
    indari
    0.36
    chairman
    0.35
    Act Density 0.001%

    No Known Activations