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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smokers
    -0.07
    ACIÓN
    -0.06
     partner
    -0.06
     싸
    -0.06
     Muhammed
    -0.06
    .animation
    -0.06
    Helvetica
    -0.06
     Lucifer
    -0.06
     tweak
    -0.06
    軍
    -0.06
    POSITIVE LOGITS
    iếm
    0.08
    ／/
    0.07
    에게
    0.06
     últimos
    0.06
    /{$
    0.06
     SearchResult
    0.06
     gratuite
    0.06
    .sync
    0.06
    िच
    0.06
     tấn
    0.06
    Act Density 0.013%

    No Known Activations