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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    积极推动
    -0.07
    坏
    -0.07
     checking
    -0.07
    дол
    -0.06
    تنفي
    -0.06
     pals
    -0.06
    getNode
    -0.06
     offspring
    -0.06
    Jos
    -0.06
    ActionCreators
    -0.06
    POSITIVE LOGITS
    ورة
    0.07
     וה
    0.07
    会议室
    0.06
    .Collection
    0.06
    ISIBLE
    0.06
    MEDIA
    0.06
    .string
    0.06
     lesen
    0.06
    嚴
    0.06
    uję
    0.06
    Act Density 0.266%

    No Known Activations