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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Role
    -0.08
    ="${
    -0.07
     Ни
    -0.07
    Roman
    -0.07
    机器人
    -0.07
     tempting
    -0.07
    (place
    -0.06
     uni
    -0.06
    NI
    -0.06
    策
    -0.06
    POSITIVE LOGITS
     ;;=
    0.07
    .real
    0.07
    pper
    0.07
    iche
    0.07
     ballots
    0.07
    即便
    0.07
     пом
    0.07
    铢
    0.07
    Ĺ
    0.07
     róż
    0.06
    Act Density 0.072%

    No Known Activations