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

    Neuronpedia

    INDEX
    Explanations

    text data training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Това
    0.46
     बीमा
    0.43
    acion
    0.41
    THERE
    0.41
     পরিষে
    0.41
     આજે
    0.41
    ové
    0.40
     মেরামত
    0.40
     Komponenten
    0.40
    櫈
    0.40
    POSITIVE LOGITS
     religion
    0.37
     dissenting
    0.36
     audience
    0.35
     adulthood
    0.35
     pointer
    0.35
     rituals
    0.34
     special
    0.32
     dictionary
    0.32
     dialect
    0.32
     text
    0.32
    Act Density 0.000%

    No Known Activations