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

    Neuronpedia

    INDEX
    Explanations

    both foundational texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Daten
    0.51
    FRE
    0.50
    एचओ
    0.50
    WEEK
    0.48
    рито
    0.48
    PDF
    0.47
    MAG
    0.47
    ﺙ
    0.47
    STORE
    0.47
     במש
    0.46
    POSITIVE LOGITS
     im
    0.44
    letion
    0.44
     repetitions
    0.44
    ឬ
    0.44
     diminution
    0.43
     πα
    0.43
    ksjon
    0.42
     annexed
    0.41
    iende
    0.41
     विद्य
    0.40
    Act Density 0.001%

    No Known Activations