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

    Neuronpedia

    INDEX
    Explanations

    Confeder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ص
    -0.07
    KE
    -0.07
    booking
    -0.07
    Á
    -0.07
    ssql
    -0.07
     perfiles
    -0.07
     برد
    -0.07
     desvi
    -0.07
    occup
    -0.07
    occupied
    -0.07
    POSITIVE LOGITS
     정부
    0.09
     সরকার
    0.08
    民
    0.08
     woes
    0.08
     hardships
    0.08
     deficiencies
    0.08
     সরকারের
    0.08
     weaknesses
    0.08
    .footer
    0.08
    弱
    0.08
    Act Density 0.001%

    No Known Activations