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

    Neuronpedia

    INDEX
    Explanations

    belt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    煊
    0.43
    弈
    0.41
    꽁
    0.39
    ುತ್ತಿರುವ
    0.39
    焲
    0.39
    晤
    0.39
    fstream
    0.38
    পর্য
    0.38
    раху
    0.38
    遒
    0.37
    POSITIVE LOGITS
     belt
    3.69
    Bel
    3.58
     Belt
    3.55
     Bel
    3.53
     belts
    3.53
     bel
    3.47
    Belt
    3.44
     BEL
    3.28
    belt
    3.27
    bel
    3.17
    Act Density 0.035%

    No Known Activations