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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     несмотря
    1.26
     inequities
    1.23
    িক্ত
    1.21
     RandomForest
    1.19
     covariance
    1.17
    スーツ
    1.17
    ০
    1.16
     intellig
    1.12
    কোন
    1.11
     homophobic
    1.10
    POSITIVE LOGITS
    ጨማሪ
    1.67
    nial
    1.62
     Downing
    1.53
     Commandments
    1.51
     háb
    1.49
    큰
    1.40
     voulu
    1.38
    त
    1.35
    nish
    1.34
     tivesse
    1.34
    Act Density 0.148%

    No Known Activations