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

    Neuronpedia

    INDEX
    Explanations

    structured subject lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     angene
    0.51
     ejemplo
    0.50
     exemple
    0.50
     sommige
    0.49
     solche
    0.49
     Eğer
    0.49
     attendre
    0.48
     exemplu
    0.48
     některé
    0.48
     Nếu
    0.47
    POSITIVE LOGITS
     and
    0.60
     &
    0.59
    System
    0.56
     (
    0.54
     system
    0.50
    制度
    0.48
    process
    0.47
    core
    0.46
    Process
    0.45
     Architecture
    0.45
    Act Density 0.119%

    No Known Activations