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

    Neuronpedia

    INDEX
    Explanations

    asking a question aloud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    譞
    0.46
    ChooseCharacter
    0.44
    告诉我
    0.41
    锴
    0.41
    説明
    0.41
    Ꭿ
    0.41
     एक्सप्लेन
    0.40
     объяс
    0.40
     მთავ
    0.40
    ableConcept
    0.39
    POSITIVE LOGITS
     voices
    0.55
     said
    0.52
    の声
    0.50
    said
    0.50
    声を
    0.49
     Despite
    0.49
    聲音
    0.49
     It
    0.47
    voices
    0.47
     Though
    0.47
    Act Density 0.002%

    No Known Activations