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

    Neuronpedia

    INDEX
    Explanations

    elasticsearch search query mapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     benefit
    0.73
     metast
    0.71
     churning
    0.71
    愉
    0.70
     wicked
    0.69
     games
    0.69
    راج
    0.69
     landfall
    0.69
     benefiting
    0.68
     النه
    0.68
    POSITIVE LOGITS
    index
    0.70
    ضاء
    0.70
    業務用
    0.68
     غلام
    0.65
     Scroll
    0.64
    𝙧
    0.63
     業務用
    0.63
    Scroll
    0.63
    PutMapping
    0.63
     scrolls
    0.63
    Act Density 0.004%

    No Known Activations