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

    Neuronpedia

    INDEX
    Explanations

    lists of attributes or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     खूबसूरत
    0.49
    فاض
    0.47
    ancipation
    0.43
     duen
    0.43
     അടി
    0.43
     красивые
    0.42
     marit
    0.41
     सुंदर
    0.41
     krás
    0.40
     красивая
    0.40
    POSITIVE LOGITS
    INE
    0.43
    CB
    0.43
    cb
    0.40
    small
    0.38
    unal
    0.38
    ério
    0.38
    IM
    0.37
    ianos
    0.37
    ERAL
    0.36
    catch
    0.36
    Act Density 0.000%

    No Known Activations