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

    Neuronpedia

    INDEX
    Explanations

    expressing opinions/disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alion
    -0.07
     pasado
    -0.07
     المهني
    -0.07
    认证
    -0.07
     ASE
    -0.07
     رقم
    -0.06
    地区的
    -0.06
    铢
    -0.06
     unp
    -0.06
    centration
    -0.06
    POSITIVE LOGITS
    的办法
    0.07
     outsiders
    0.07
    _IB
    0.07
    _specs
    0.07
    estring
    0.07
    Opened
    0.07
     صف
    0.07
    GIN
    0.07
    OD
    0.07
    bows
    0.07
    Act Density 0.018%

    No Known Activations