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

    Neuronpedia

    INDEX
    Explanations

    explaining a result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यर
    0.57
    em
    0.56
     Taxes
    0.55
    ्तिक
    0.54
     городах
    0.54
    म
    0.53
    pflege
    0.52
     Thoughts
    0.51
     Música
    0.51
    m
    0.51
    POSITIVE LOGITS
    с
    0.62
     is
    0.59
     that
    0.57
     specialized
    0.57
     thrives
    0.56
    س
    0.56
     technician
    0.55
     specializes
    0.54
     lucrat
    0.54
     booted
    0.53
    Act Density 0.001%

    No Known Activations