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

    Neuronpedia

    INDEX
    Explanations

    names of authors and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    0.48
     even
    0.46
     though
    0.44
     picture
    0.43
     and
    0.41
     as
    0.40
     -
    0.40
     very
    0.40
    ,
    0.40
     prime
    0.37
    POSITIVE LOGITS
     ಅಂಶ
    0.40
     menurunkan
    0.39
    ahydro
    0.38
    కోండి
    0.38
    ashov
    0.38
    ವಿದೆ
    0.37
     সংবাদদাতা
    0.36
     EXEMPL
    0.36
    ಕ್ಕಿಂತ
    0.36
     ಚುನಾವಣ
    0.36
    Act Density 0.000%

    No Known Activations