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

    Neuronpedia

    INDEX
    Explanations

    spike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coping
    0.43
    oxid
    0.40
     annuities
    0.38
     fatal
    0.37
    кович
    0.37
     मनाने
    0.37
     Keg
    0.35
    Keg
    0.35
    ್ಧ
    0.35
    ovia
    0.35
    POSITIVE LOGITS
     sank
    0.46
     thoughtfully
    0.43
    暂停
    0.42
     pausing
    0.41
     himself
    0.41
     Mullins
    0.40
     Shik
    0.39
     hesitate
    0.38
     mum
    0.38
    沇
    0.38
    Act Density 0.000%

    No Known Activations