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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _folder
    -0.06
    علوم
    -0.06
    錄
    -0.06
    �
    -0.06
     params
    -0.06
     Haw
    -0.06
     mark
    -0.06
    寫
    -0.06
    �
    -0.06
     cabinets
    -0.06
    POSITIVE LOGITS
    ereg
    0.07
     функ
    0.07
     katıl
    0.07
    eer
    0.07
     jetzt
    0.07
     Opera
    0.07
    "));
↵
↵
    0.07
    (cube
    0.06
    .submit
    0.06
    .workspace
    0.06
    Act Density 0.017%

    No Known Activations