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

    Neuronpedia

    INDEX
    Explanations

    world, reaction, root, force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eleições
    0.53
    GEBURTS
    0.52
    佈
    0.52
     STRU
    0.50
     важли
    0.50
    缫
    0.49
    ZO
    0.49
    बीन
    0.47
     袋
    0.46
    holung
    0.46
    POSITIVE LOGITS
     world
    0.56
    world
    0.52
    સ્
    0.49
    World
    0.47
    N
    0.46
    申
    0.46
    有没有
    0.46
    日付
    0.46
     reaction
    0.45
    世界
    0.45
    Act Density 0.000%

    No Known Activations