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

    Neuronpedia

    INDEX
    Explanations

    structuring or describing changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.50
     a
    0.48
     v
    0.47
     body
    0.45
    v
    0.41
    0.40
    g
    0.40
    օ
    0.39
     cet
    0.39
     e
    0.39
    POSITIVE LOGITS
    Prothorax
    0.50
    Kyle
    0.44
    تباينه
    0.42
    ﮩ
    0.42
    Diethyl
    0.41
    Standalone
    0.40
    RxDocument
    0.40
     مشینوں
    0.39
    ELLOW
    0.39
     prépuce
    0.39
    Act Density 0.000%

    No Known Activations