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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $con
    -0.07
     FM
    -0.07
     fisse
    -0.07
    Im
    -0.06
    fuse
    -0.06
     repeal
    -0.06
     logout
    -0.06
     molt
    -0.06
    _finder
    -0.06
    Config
    -0.06
    POSITIVE LOGITS
    ตรว
    0.07
    交流
    0.06
     incompetent
    0.06
     τρο
    0.06
     устройства
    0.06
    ん
    0.06
    floor
    0.06
    ��
    0.06
     dared
    0.06
     �
    0.06
    Act Density 0.041%

    No Known Activations