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

    Neuronpedia

    INDEX
    Explanations

    Standalone letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erotisk
    -0.06
     eagle
    -0.06
     Evangel
    -0.06
     Leap
    -0.06
    ivot
    -0.06
     narrative
    -0.06
    ential
    -0.06
     blast
    -0.06
     spanking
    -0.06
     lựa
    -0.06
    POSITIVE LOGITS
     unemployment
    0.06
    /banner
    0.06
     bef
    0.06
     مشاهده
    0.06
    фи
    0.06
     tired
    0.06
    asyarak
    0.06
    (dt
    0.06
    ров
    0.06
     ConnectionState
    0.06
    Act Density 0.015%

    No Known Activations