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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेप
    -0.07
     지방
    -0.06
    Forever
    -0.06
    preview
    -0.06
    elope
    -0.06
     Tops
    -0.06
     pear
    -0.06
     etree
    -0.06
     cuốn
    -0.06
    WORD
    -0.06
    POSITIVE LOGITS
    _FLAGS
    0.07
    ัดการ
    0.06
    ematic
    0.06
    itudes
    0.06
    ermal
    0.06
     Polish
    0.06
    afc
    0.06
     Republicans
    0.06
    hores
    0.06
    .LINE
    0.06
    Act Density 0.344%

    No Known Activations