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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     化
    -0.07
    [S
    -0.07
    ！”
    -0.06
    .Prop
    -0.06
    ortality
    -0.06
     probing
    -0.06
     tính
    -0.06
    ismo
    -0.06
    !"
    -0.06
    роп
    -0.06
    POSITIVE LOGITS
    包
    0.07
    cházet
    0.06
    ई
    0.06
     outstanding
    0.06
     þ
    0.06
    _refresh
    0.06
     martin
    0.06
     імен
    0.06
     Newark
    0.06
     growing
    0.06
    Act Density 0.005%

    No Known Activations