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

    Neuronpedia

    INDEX
    Explanations

    scientific results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bram
    -0.07
     이제
    -0.07
    ERVER
    -0.06
     の
    -0.06
     Magic
    -0.06
     =↵↵
    -0.06
    域
    -0.06
    grey
    -0.06
    hes
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    atab
    0.07
    ATAB
    0.07
    tur
    0.06
    ographer
    0.06
    urous
    0.06
    arbonate
    0.06
    wealth
    0.06
    MMC
    0.06
    webkit
    0.06
     ramen
    0.06
    Act Density 0.074%

    No Known Activations