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

    Neuronpedia

    INDEX
    Explanations

    technical and domain-specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.56
    Pentru
    0.54
    Baik
    0.54
     dieses
    0.54
    Jeśli
    0.53
    ك
    0.53
    Für
    0.52
     harp
    0.52
    د
    0.52
    א
    0.51
    POSITIVE LOGITS
    溶液
    0.53
     ছাত্রী
    0.50
     देरी
    0.49
    üğü
    0.46
    腻
    0.46
    出来的
    0.45
    iffel
    0.45
    imek
    0.45
     இல
    0.45
     hơi
    0.45
    Act Density 0.000%

    No Known Activations