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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    开辟
    -0.07
     stubborn
    -0.07
     sıc
    -0.07
    货
    -0.07
     đảo
    -0.06
     Pon
    -0.06
     Mud
    -0.06
    佯
    -0.06
    也不敢
    -0.06
    巇
    -0.06
    POSITIVE LOGITS
    indow
    0.08
     appellant
    0.07
    累积
    0.07
    卧室
    0.07
    /DD
    0.07
    瑬
    0.07
    ({})↵
    0.07
     putt
    0.07
    尽情
    0.07
    lâ
    0.07
    Act Density 0.005%

    No Known Activations