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

    Neuronpedia

    INDEX
    Explanations

    * Basic Categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нейтро
    0.46
    ຢ່າງ
    0.45
    ARAJ
    0.42
    idcoin
    0.41
    рай
    0.41
    垶
    0.40
    嗄
    0.40
     اگلے
    0.40
    ᾳ
    0.40
    pdb
    0.40
    POSITIVE LOGITS
     activity
    0.52
     often
    0.48
     alive
    0.48
     peace
    0.45
     basement
    0.45
     baggage
    0.44
     good
    0.44
     space
    0.44
     entertainment
    0.44
     ab
    0.44
    Act Density 0.000%

    No Known Activations