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

    Neuronpedia

    INDEX
    Explanations

    code and grammars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _spec
    -0.07
     isa
    -0.07
     crosses
    -0.07
     Ja
    -0.07
    金币
    -0.07
    .TextChanged
    -0.06
    (Configuration
    -0.06
    ston
    -0.06
    Cons
    -0.06
     Lola
    -0.06
    POSITIVE LOGITS
     Iranians
    0.07
    issors
    0.07
    麻将
    0.07
    ления
    0.07
    팰
    0.07
     ward
    0.07
    pth
    0.07
     UPS
    0.06
    _tracks
    0.06
    IMATE
    0.06
    Act Density 0.013%

    No Known Activations