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

    Neuronpedia

    INDEX
    Explanations

    numpy in python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ONU
    0.78
    ̣c
    0.72
    มะ
    0.69
    Hemat
    0.69
    ("'
    0.68
    Milliseconds
    0.68
    (")
    0.66
     povez
    0.66
     Alors
    0.65
     Haemat
    0.65
    POSITIVE LOGITS
    from
    0.69
     корреспонд
    0.69
     from
    0.67
    ável
    0.66
     installed
    0.66
     embarked
    0.65
     sighted
    0.64
    وتا
    0.64
    ويت
    0.64
     conhecimento
    0.63
    Act Density 0.006%

    No Known Activations