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

    Neuronpedia

    INDEX
    Explanations

    concept attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     চলচ্চিত্রে
    0.37
    {~
    0.36
    laboratory
    0.34
     상세보기
    0.34
    television
    0.34
     मानचित्र
    0.33
    Laboratory
    0.33
     애플
    0.33
    로부터
    0.33
     utilizzando
    0.33
    POSITIVE LOGITS
     thing
    0.62
     stuff
    0.62
     info
    0.55
     guy
    0.53
     ones
    0.50
     etc
    0.49
     pics
    0.49
     docs
    0.48
     devs
    0.48
     guys
    0.47
    Act Density 0.185%

    No Known Activations