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

    Neuronpedia

    INDEX
    Explanations

    sprawling stories and managed systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sample
    0.47
    MEs
    0.47
     latch
    0.47
    ore
    0.45
     rope
    0.45
     he
    0.45
     schedule
    0.43
    he
    0.43
    गित
    0.43
     negotiations
    0.42
    POSITIVE LOGITS
    Pow
    0.43
     више
    0.42
     Conseils
    0.41
     மூன்ற
    0.41
    美容
    0.41
    ඤ
    0.40
     finement
    0.40
     dần
    0.40
    ickým
    0.40
     δύ
    0.40
    Act Density 0.001%

    No Known Activations