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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规
    -0.07
    Bon
    -0.06
     Leonardo
    -0.06
    名字
    -0.06
     глаз
    -0.06
     계속
    -0.06
     اک
    -0.06
     의
    -0.06
    .compare
    -0.06
     academics
    -0.06
    POSITIVE LOGITS
    ゞ
    0.07
     FORCE
    0.07
    camatan
    0.07
    */
    0.06
     предус
    0.06
    elsen
    0.06
    '],$_
    0.06
    ']=
    0.06
    ]\
    0.06
     имму
    0.06
    Act Density 0.030%

    No Known Activations