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

    Neuronpedia

    INDEX
    Explanations

    specific categories or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contraceptives
    0.54
    थिक
    0.51
    riya
    0.50
    itation
    0.50
    ૉ
    0.48
     वस्तू
    0.46
    ama
    0.46
    ल्स
    0.46
    Athlete
    0.46
    ry
    0.45
    POSITIVE LOGITS
     sonra
    0.44
    함으로써
    0.43
     दरवाजे
    0.43
     sebagai
    0.42
     kao
    0.41
     hydrolysis
    0.40
     "".
    0.40
     pow
    0.40
     como
    0.40
     SH
    0.39
    Act Density 0.002%

    No Known Activations