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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Comfort
    -0.07
     המרכזי
    -0.07
    👖
    -0.07
     committee
    -0.07
    ומו
    -0.06
    /rem
    -0.06
    /end
    -0.06
     Tol
    -0.06
    /change
    -0.06
     Guinness
    -0.06
    POSITIVE LOGITS
    тер
    0.07
    Ports
    0.07
    出租车
    0.07
     Cougar
    0.07
     تس
    0.06
    伯
    0.06
    bug
    0.06
    护士
    0.06
    .network
    0.06
     mux
    0.06
    Act Density 0.041%

    No Known Activations