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

    Neuronpedia

    INDEX
    Explanations

    document formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     порядке
    -0.07
    🍙
    -0.07
    *q
    -0.07
     zoals
    -0.07
     meis
    -0.07
    ヮ
    -0.06
    utura
    -0.06
    Wins
    -0.06
    ima
    -0.06
     Particularly
    -0.06
    POSITIVE LOGITS
     COVID
    0.07
    起重机
    0.07
     Lean
    0.07
     ingest
    0.07
     defects
    0.07
    开源
    0.07
     그것
    0.06
     Elementary
    0.06
    grim
    0.06
     medications
    0.06
    Act Density 0.032%

    No Known Activations