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

    Neuronpedia

    INDEX
    Explanations

    adding music, spells, waves, areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kern
    0.52
     policies
    0.44
     mock
    0.43
     toilet
    0.42
     dress
    0.41
     wine
    0.41
     grace
    0.39
     irrigation
    0.39
     highland
    0.39
     restroom
    0.39
    POSITIVE LOGITS
    Worlds
    0.41
    从中
    0.40
    愔
    0.40
    bel
    0.39
    了一个
    0.38
    elfalt
    0.38
    各有
    0.38
    懈
    0.38
    Jung
    0.38
     वर्ल्ड
    0.37
    Act Density 0.000%

    No Known Activations