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

    Neuronpedia

    INDEX
    Explanations

    in a way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warranties
    1.26
     '.';
    1.25
     prothorax
    1.25
     पड़ी
    1.24
     അടുത്ത
    1.22
     hassles
    1.21
     resumes
    1.21
     Bezeichnung
    1.19
     ভুট্টো
    1.18
     nymphs
    1.18
    POSITIVE LOGITS
     stanow
    1.09
    as
    1.03
    рак
    1.02
    إ
    1.02
     vyp
    1.00
    individual
    0.99
    뚝
    0.98
    arrest
    0.97
    ாரி
    0.97
    που
    0.96
    Act Density 0.000%

    No Known Activations