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

    Neuronpedia

    INDEX
    Explanations

    reinforcement learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rollout
    -0.78
    Subview
    -0.72
    чти
    -0.71
    odule
    -0.71
     בו
    -0.71
    ။
    -0.69
     Rican
    -0.68
     pribadi
    -0.68
     gast
    -0.66
     rolled
    -0.66
    POSITIVE LOGITS
     comentó
    0.76
    LEARNING
    0.76
    সূত্র
    0.72
    watching
    0.72
     CRUD
    0.71
     GLUT
    0.70
     établissements
    0.69
    UKA
    0.69
     Baird
    0.69
    Networking
    0.69
    Act Density 0.005%

    No Known Activations