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

    Neuronpedia

    INDEX
    Explanations

    established

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ственное
    -0.07
    اسي
    -0.06
     cih
    -0.06
    важ
    -0.06
     eux
    -0.06
    ху
    -0.06
     اين
    -0.06
    む
    -0.06
     UserRole
    -0.06
    Essay
    -0.06
    POSITIVE LOGITS
     established
    0.09
    -known
    0.08
     chop
    0.07
     establish
    0.07
     accom
    0.07
     останов
    0.07
     familiar
    0.07
     known
    0.06
    ="<?=$
    0.06
     thermometer
    0.06
    Act Density 0.020%

    No Known Activations