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

    Neuronpedia

    INDEX
    Explanations

    ranges and estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مله
    0.45
    presentableId
    0.40
    λλην
    0.38
    perplexity
    0.38
     পারেনা
    0.36
    ُم
    0.36
    schools
    0.36
    تباينه
    0.35
    льнай
    0.35
    🤧
    0.35
    POSITIVE LOGITS
    Siem
    0.42
     gun
    0.42
    ρίου
    0.42
     تیاری
    0.40
     weapon
    0.40
     Weapon
    0.40
     공격
    0.40
    ignition
    0.40
     Konto
    0.40
    কের
    0.39
    Act Density 0.006%

    No Known Activations