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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ительные
    -0.06
    TEL
    -0.06
    Customers
    -0.06
     첫
    -0.06
     arguably
    -0.06
    _employee
    -0.06
     전용면적
    -0.06
    wy
    -0.06
     avoir
    -0.05
    privation
    -0.05
    POSITIVE LOGITS
     non
    0.09
     Eclipse
    0.08
     Non
    0.08
     نام
    0.07
    non
    0.07
     examine
    0.07
     паци
    0.07
     만족
    0.06
    #End
    0.06
     Temp
    0.06
    Act Density 0.000%

    No Known Activations