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

    Neuronpedia

    INDEX
    Explanations

    Product model numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hanson
    -0.07
     answered
    -0.07
     commune
    -0.06
     Heritage
    -0.06
     Shank
    -0.06
     Arrest
    -0.06
     dalších
    -0.06
    sleep
    -0.06
     Slater
    -0.06
    파트
    -0.06
    POSITIVE LOGITS
    ец
    0.07
     диаг
    0.07
    шись
    0.06
     tah
    0.06
     talents
    0.06
    dü
    0.06
    piry
    0.06
     про
    0.06
    الم
    0.06
     四
    0.06
    Act Density 0.018%

    No Known Activations