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

    Neuronpedia

    INDEX
    Explanations

    cutting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     federally
    -0.07
     collaborations
    -0.07
    แฟ
    -0.07
    /lists
    -0.06
     리그
    -0.06
     modele
    -0.06
     mosque
    -0.06
     христи
    -0.06
    datagrid
    -0.06
     г
    -0.06
    POSITIVE LOGITS
     pickups
    0.08
     Cater
    0.07
    球
    0.07
     भव
    0.07
    _Image
    0.06
    чої
    0.06
     chewing
    0.06
     Bulld
    0.06
     unfold
    0.06
    .scroll
    0.06
    Act Density 0.006%

    No Known Activations