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

    Neuronpedia

    INDEX
    Explanations

    linguist, vector, realistic, MLP, files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificados
    0.48
    verde
    0.48
     шка
    0.46
    sleep
    0.44
    igned
    0.43
    wig
    0.43
    nati
    0.43
    ಲ್ಲೂ
    0.42
    тором
    0.42
    onnaise
    0.42
    POSITIVE LOGITS
     prevede
    0.51
     toolbar
    0.50
     tạo
    0.49
     eszk
    0.45
     CV
    0.45
     område
    0.45
     Toolbar
    0.44
     profondeur
    0.44
    ریر
    0.43
     fonctionne
    0.43
    Act Density 0.001%

    No Known Activations