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

    Neuronpedia

    INDEX
    Explanations

    restaurant reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atte
    -0.07
     Judges
    -0.07
    (source
    -0.06
     cra
    -0.06
    osten
    -0.06
    忍
    -0.06
     demean
    -0.06
     Tender
    -0.06
    soft
    -0.06
    愛
    -0.06
    POSITIVE LOGITS
    .ws
    0.07
    _episode
    0.07
     rámci
    0.07
     ;;^
    0.06
     zahrn
    0.06
    “,
    0.06
     implicitly
    0.06
    lamış
    0.06
    .Exists
    0.06
    -build
    0.06
    Act Density 0.025%

    No Known Activations