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

    Neuronpedia

    INDEX
    Explanations

    Unity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parker
    -0.07
    fileName
    -0.07
    ，则
    -0.07
     bella
    -0.07
     sûr
    -0.07
    чика
    -0.07
    ाओ
    -0.07
     itibar
    -0.07
    539
    -0.07
    usually
    -0.07
    POSITIVE LOGITS
     Trinity
    0.09
     unity
    0.08
     Unity
    0.08
    nty
    0.07
     Union
    0.07
    ulty
    0.07
    union
    0.07
     vý
    0.07
     unit
    0.07
    uti
    0.07
    Act Density 0.003%

    No Known Activations