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

    Neuronpedia

    INDEX
    Explanations

    vocabulary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dataList
    -0.07
    Letters
    -0.06
    Estimated
    -0.06
     Pew
    -0.06
     Hun
    -0.06
     Vys
    -0.06
     overcoming
    -0.06
    ється
    -0.06
     doen
    -0.06
    婦
    -0.06
    POSITIVE LOGITS
    (None
    0.07
    .launch
    0.06
     های
    0.06
    (Byte
    0.06
    []){↵
    0.06
    .col
    0.06
    های
    0.06
     unve
    0.06
          
    0.06
    ，“
    0.06
    Act Density 0.024%

    No Known Activations