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

    Neuronpedia

    INDEX
    Explanations

    question and answer starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hydrolyzed
    0.35
    0.35
     ار
    0.31
     promulgated
    0.30
    ്രി
    0.30
     pamoja
    0.30
     droplets
    0.29
     pochi
    0.29
     جنس
    0.29
     مس
    0.28
    POSITIVE LOGITS
    hetical
    0.35
    푎
    0.35
    érience
    0.34
    :~
    0.34
    ३
    0.34
    另一
    0.33
    matig
    0.33
     मसलन
    0.33
    imantan
    0.33
     मानता
    0.33
    Act Density 0.113%

    No Known Activations