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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dinero
    -0.07
    trer
    -0.07
     RouterModule
    -0.06
     posto
    -0.06
     bills
    -0.06
     managerial
    -0.06
     flow
    -0.06
     booked
    -0.06
    _done
    -0.06
    xde
    -0.06
    POSITIVE LOGITS
    Southern
    0.07
     Southeast
    0.07
     Sunder
    0.06
     identifiable
    0.06
    FullYear
    0.06
    theast
    0.06
     afar
    0.06
    虫
    0.06
    maximum
    0.06
    isEqual
    0.06
    Act Density 0.017%

    No Known Activations