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

    Neuronpedia

    INDEX
    Explanations

    irrespective of, no matter how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mainly
    0.47
     mainly
    0.45
     Mainly
    0.45
     inhaled
    0.40
     pipeline
    0.40
    Preference
    0.39
    pipeline
    0.39
    ⿶
    0.39
     Preference
    0.39
     overall
    0.39
    POSITIVE LOGITS
     funda
    0.49
     Woh
    0.45
     believable
    0.44
    !(
    0.42
     भला
    0.41
     quizz
    0.40
     plausible
    0.39
    টা
    0.39
     ไอ้
    0.38
     sane
    0.38
    Act Density 0.001%

    No Known Activations