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

    Neuronpedia

    INDEX
    Explanations

    physics, power, cancer, mechanical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inasmuch
    0.43
    куда
    0.42
    ckpt
    0.41
    EDGE
    0.40
     сатып
    0.40
    ರೇ
    0.40
    dex
    0.39
     ಗುರು
    0.39
    唪
    0.38
     mView
    0.38
    POSITIVE LOGITS
    Ant
    0.46
    ální
    0.45
     plantas
    0.42
     horror
    0.42
     fashioned
    0.41
     belle
    0.40
    φη
    0.40
     Twitch
    0.40
     folk
    0.39
     técnicas
    0.39
    Act Density 0.001%

    No Known Activations