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

    Neuronpedia

    INDEX
    Explanations

    needing help or advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mickey
    -0.08
     applaud
    -0.07
    ґ
    -0.07
    现实中
    -0.07
    밉
    -0.07
    这种
    -0.07
    ckså
    -0.07
    IsNull
    -0.07
     medio
    -0.07
    ']]]↵
    -0.07
    POSITIVE LOGITS
     bag
    0.07
     Fall
    0.06
     come
    0.06
     Hà
    0.06
    Culture
    0.06
    감
    0.06
     snake
    0.06
     Lots
    0.06
     Version
    0.06
    �습니다
    0.06
    Act Density 0.056%

    No Known Activations