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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cabinets
    -0.07
    ीग
    -0.07
    (lista
    -0.07
     Demon
    -0.06
    hammer
    -0.06
     Infinite
    -0.06
    ieving
    -0.06
    DbContext
    -0.06
    Besides
    -0.06
     Nobel
    -0.06
    POSITIVE LOGITS
     engraved
    0.07
    Mos
    0.06
     possono
    0.06
     getResources
    0.06
    toJson
    0.06
     einzel
    0.06
     sodom
    0.06
     yaz
    0.06
    ές
    0.06
     (){↵
    0.06
    Act Density 0.002%

    No Known Activations