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

    Neuronpedia

    INDEX
    Explanations

    operation or system components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nal
    0.50
     Moc
    0.48
    쐞
    0.48
     Coco
    0.48
     Stuart
    0.47
    щер
    0.46
    Ꮪ
    0.46
    ੈਂ
    0.46
    Niger
    0.45
     Scha
    0.44
    POSITIVE LOGITS
     actuators
    0.46
     وتر
    0.46
     ليست
    0.45
    发动机
    0.45
     betreff
    0.44
     pessoais
    0.44
     опера
    0.43
     تمر
    0.43
     operate
    0.43
     engines
    0.43
    Act Density 0.000%

    No Known Activations