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

    Neuronpedia

    INDEX
    Explanations

    episode number or title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     your
    0.78
     it
    0.74
     iyong
    0.66
    ಕಿ
    0.65
    it
    0.63
    ಇ
    0.63
     itp
    0.62
    aktif
    0.61
    as
    0.60
     annoying
    0.59
    POSITIVE LOGITS
    راس
    0.50
    nymi
    0.50
    的大
    0.50
    "
    0.50
     cuối
    0.49
    నూ
    0.49
    ská
    0.48
    ोत्सव
    0.48
    րան
    0.48
     visc
    0.47
    Act Density 0.005%

    No Known Activations