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

    Neuronpedia

    INDEX
    Explanations

    matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    情侣
    -0.07
     erót
    -0.07
    主題
    -0.07
    hone
    -0.07
     boss
    -0.07
    奏
    -0.07
    妹子
    -0.07
     focus
    -0.06
    ⇑
    -0.06
     tempList
    -0.06
    POSITIVE LOGITS
     By
    0.08
     أل
    0.08
     Income
    0.07
    اخت
    0.07
     webs
    0.07
     BehaviorSubject
    0.07
     dull
    0.07
     יש
    0.07
    嚆
    0.07
     Wr
    0.07
    Act Density 0.004%

    No Known Activations