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

    Neuronpedia

    INDEX
    Explanations

    introduces the subject of discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    合計
    0.50
     groupe
    0.46
    Cla
    0.46
    }]\
    0.46
    igence
    0.46
     revend
    0.46
    訲
    0.45
     ইলেক্ট্রো
    0.45
     종합
    0.45
    criteria
    0.44
    POSITIVE LOGITS
     vampire
    0.53
    ње
    0.47
    蠶
    0.44
     predator
    0.44
     lathe
    0.43
     screening
    0.41
    娃
    0.41
    тел
    0.41
     herb
    0.40
    ινων
    0.40
    Act Density 0.002%

    No Known Activations