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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Road
    -0.08
    antiago
    -0.06
     allowances
    -0.06
    AccountId
    -0.06
     trunc
    -0.06
     Cru
    -0.06
    ráci
    -0.06
     тон
    -0.06
    ppt
    -0.06
     Adjustment
    -0.06
    POSITIVE LOGITS
    templates
    0.07
     actresses
    0.07
    .onResume
    0.06
     Nearly
    0.06
    itational
    0.06
    .optimize
    0.06
    noop
    0.06
    _walk
    0.06
    _->
    0.06
     disponibles
    0.06
    Act Density 0.006%

    No Known Activations