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

    Neuronpedia

    INDEX
    Explanations

    matrix and tensor ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recib
    0.56
    ગાહી
    0.50
    0.47
     మీకు
    0.46
     അഭിപ്
    0.46
    㛣
    0.46
    સાર
    0.45
    olia
    0.45
    మ్యాచ్
    0.45
    ಡಿ
    0.45
    POSITIVE LOGITS
     εξ
    0.48
    :
    0.48
     engineer
    0.47
     supply
    0.45
     :
    0.45
    ્ર
    0.44
    リ
    0.44
     engineers
    0.42
     supplying
    0.42
     اخیر
    0.42
    Act Density 0.001%

    No Known Activations