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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     法
    -0.07
     prick
    -0.07
     zona
    -0.07
     desea
    -0.06
     duro
    -0.06
    EXPECTED
    -0.06
     Andr
    -0.06
     roky
    -0.06
     noche
    -0.06
     pastor
    -0.06
    POSITIVE LOGITS
     Smoke
    0.07
     childcare
    0.06
    ło
    0.06
    Definition
    0.06
    ItemType
    0.06
    bib
    0.06
    .undefined
    0.06
    	dd
    0.06
    typedef
    0.06
    挙
    0.06
    Act Density 0.003%

    No Known Activations