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

    Neuronpedia

    INDEX
    Explanations

    language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ipation
    0.41
    들
    0.39
    Nich
    0.38
    Didn
    0.35
     deprive
    0.35
     заня
    0.34
    대한
    0.34
     مادر
    0.34
    능
    0.34
    ريقة
    0.33
    POSITIVE LOGITS
     FF
    0.77
     BB
    0.73
     MM
    0.72
     GG
    0.71
     LL
    0.71
     KK
    0.70
     HH
    0.70
     BBB
    0.67
     VV
    0.67
     JJ
    0.66
    Act Density 0.049%

    No Known Activations