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

    Neuronpedia

    INDEX
    Explanations

    Russian model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्करण
    0.51
    শিংটন
    0.51
     ذریع
    0.47
     وړاندوینه
    0.47
     সতীশ
    0.46
    嚗
    0.46
     danych
    0.46
     circunfer
    0.46
     drivetrain
    0.46
     curviliné
    0.46
    POSITIVE LOGITS
     А
    0.61
     Ка
    0.59
     У
    0.57
     С
    0.57
     в
    0.56
     З
    0.56
     П
    0.56
     Ку
    0.56
     по
    0.55
     на
    0.54
    Act Density 0.034%

    No Known Activations