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

    Neuronpedia

    INDEX
    Explanations

    live

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dim
    -0.07
    맞
    -0.07
    :")↵
    -0.07
    ij
    -0.07
     Cumberland
    -0.07
    .Asset
    -0.07
    砹
    -0.06
     seasoned
    -0.06
    ︓
    -0.06
    iesz
    -0.06
    POSITIVE LOGITS
     เมษายน
    0.07
    麻烦
    0.07
    𝖗
    0.07
     ??
    0.06
    円
    0.06
    UTURE
    0.06
    ;?>"
    0.06
    劳动
    0.06
    ラ
    0.06
    Λ
    0.06
    Act Density 0.017%

    No Known Activations