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

    Neuronpedia

    INDEX
    Explanations

    how to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sair
    0.48
     perfil
    0.45
    是从
    0.44
    恤
    0.44
    icija
    0.43
    族的
    0.43
    গির
    0.42
    성과
    0.42
    族
    0.42
    兮
    0.41
    POSITIVE LOGITS
    ningen
    0.52
     Venice
    0.52
    кха
    0.47
     Shipbuilding
    0.47
     btw
    0.46
     downfall
    0.45
     billionaire
    0.45
     ویڈیو
    0.45
     देखील
    0.44
     প্রভাস
    0.44
    Act Density 0.003%

    No Known Activations