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

    Neuronpedia

    INDEX
    Explanations

    constant or literal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рус
    -0.07
    handler
    -0.07
     Overwatch
    -0.06
    움
    -0.06
    τζ
    -0.06
    スレ
    -0.06
    Winvalid
    -0.06
    _numer
    -0.06
    .Xr
    -0.06
     Democracy
    -0.06
    POSITIVE LOGITS
    .ejb
    0.07
    .call
    0.06
     Claire
    0.06
    riet
    0.06
     Chúa
    0.06
     coli
    0.06
    .core
    0.06
     Phi
    0.06
    /App
    0.06
     chef
    0.06
    Act Density 0.035%

    No Known Activations