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

    Neuronpedia

    INDEX
    Explanations

    cart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rare
    -0.07
    环境
    -0.07
     Responsible
    -0.07
     dozen
    -0.07
     Kindle
    -0.06
    �
    -0.06
     Iran
    -0.06
    뚫
    -0.06
    ."""
    -0.06
    على
    -0.06
    POSITIVE LOGITS
    ❢
    0.09
    vie
    0.07
    ㎯
    0.07
    _DC
    0.07
    احتجاج
    0.07
     endorsing
    0.07
     [|
    0.07
    xdc
    0.07
     bỏ
    0.07
    龂
    0.07
    Act Density 0.056%

    No Known Activations