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

    Neuronpedia

    INDEX
    Explanations

    reinforcement learning and rewards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    графі
    0.65
     रोजिक
    0.60
     kube
    0.59
    ING
    0.58
    埕
    0.58
    М
    0.55
     көр
    0.54
     lysosomes
    0.54
     Hälfte
    0.54
    lympi
    0.53
    POSITIVE LOGITS
     reward
    0.75
    reward
    0.67
    el
    0.64
    a
    0.64
    al
    0.62
    </h3>
    0.61
    of
    0.57
    il
    0.55
     rewards
    0.55
    forcement
    0.54
    Act Density 0.044%

    No Known Activations