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

    Neuronpedia

    INDEX
    Explanations

    examples, why, what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chaining
    0.44
    ↵↵
    0.43
     chained
    0.43
    rahm
    0.41
     Staub
    0.41
     Noether
    0.40
     consulted
    0.39
    شاف
    0.39
     coval
    0.39
    τρέ
    0.39
    POSITIVE LOGITS
     వైసీపీ
    0.50
    eşit
    0.50
     auspicious
    0.49
    ide
    0.49
    adaan
    0.48
     प्रतिरक्षा
    0.47
     誕生日
    0.47
     आईटी
    0.47
    akaan
    0.47
     प्रीत
    0.47
    Act Density 0.002%

    No Known Activations