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

    Neuronpedia

    INDEX
    Explanations

    numbers and simple words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (),"
    0.73
     conforming
    0.71
     supposedly
    0.68
     (“
    0.68
     (‘
    0.65
    ","
    0.65
     ("
    0.64
     {"
    0.64
    ','
    0.64
    －－
    0.62
    POSITIVE LOGITS
     yine
    0.85
     rimane
    0.81
    říve
    0.80
     tinham
    0.80
     కూడా
    0.79
     aussi
    0.78
     সর্বদা
    0.78
    stitute
    0.77
     মতোই
    0.77
     কে
    0.77
    Act Density 0.437%

    No Known Activations