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

    Neuronpedia

    INDEX
    Explanations

    census, area, demographics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bew
    -0.08
    coop
    -0.07
    닛
    -0.07
    reuse
    -0.07
     talking
    -0.06
     toilet
    -0.06
     offsets
    -0.06
    𝐖
    -0.06
    /arch
    -0.06
    (co
    -0.06
    POSITIVE LOGITS
    经济增长
    0.08
    ="/">↵
    0.07
    财富
    0.07
     الفنان
    0.07
     below
    0.07
     Lar
    0.07
    ("""↵
    0.07
    ása
    0.07
    �
    0.07
    -expand
    0.07
    Act Density 0.115%

    No Known Activations