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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Least
    -0.06
    ísto
    -0.06
    naires
    -0.06
     leth
    -0.06
     Thorn
    -0.06
    _ADD
    -0.06
    vable
    -0.06
    -directed
    -0.06
     look
    -0.06
    搞
    -0.06
    POSITIVE LOGITS
     |
    0.08
     информ
    0.07
     shemale
    0.06
     брат
    0.06
     oppressive
    0.06
    成绩
    0.06
    ımızı
    0.06
     aboard
    0.06
    =status
    0.06
    /public
    0.06
    Act Density 0.007%

    No Known Activations