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

    Neuronpedia

    INDEX
    Explanations

    decision and action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     receb
    0.39
     शेवट
    0.38
     beachten
    0.37
    बा
    0.37
     grievances
    0.37
     tránh
    0.37
    "。
    0.35
     юк
    0.35
     ontvangen
    0.35
    巴
    0.35
    POSITIVE LOGITS
     decidió
    0.60
     решил
    0.59
     decided
    0.57
     решили
    0.55
     покуп
    0.54
    早速
    0.53
    决定
    0.51
     décidé
    0.51
     daraus
    0.49
     решила
    0.49
    Act Density 0.063%

    No Known Activations