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

    Neuronpedia

    INDEX
    Explanations

    howcorrectlycalmlyslowlyquicklypeacefully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    degenerative
    0.70
    apoptotic
    0.61
    uyentes
    0.59
    renowned
    0.59
    监
    0.57
     एकमात्र
    0.55
     প্রশ্নে
    0.54
    Ethn
    0.54
    नेश
    0.54
     ఉంటు
    0.54
    POSITIVE LOGITS
     quietly
    1.03
     things
    0.96
     calmly
    0.91
     correctement
    0.90
     correctly
    0.89
     corretamente
    0.88
     properly
    0.85
     slowly
    0.85
     quickly
    0.82
     peacefully
    0.81
    Act Density 0.089%

    No Known Activations