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

    Neuronpedia

    INDEX
    Explanations

    Romance language suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visited
    -0.06
     میشود
    -0.06
     supply
    -0.06
    .Cookies
    -0.06
    ší
    -0.06
    AP
    -0.06
    _sheet
    -0.06
     Oil
    -0.06
    _files
    -0.06
     shl
    -0.06
    POSITIVE LOGITS
     republik
    0.07
    ЛЬ
    0.06
     getActivity
    0.06
     Flake
    0.06
     @"\
    0.06
     youngest
    0.06
    }@
    0.06
    艇
    0.06
    ��
    0.06
     функ
    0.06
    Act Density 0.071%

    No Known Activations