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

    Neuronpedia

    INDEX
    Explanations

    explicit content and intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Leuven
    0.39
     Stratford
    0.37
     Getty
    0.37
    ম্ত
    0.36
     Rotterdam
    0.36
    †
    0.35
     お知らせ
    0.35
     Amsterdam
    0.35
     বরাত
    0.34
     †
    0.33
    POSITIVE LOGITS
    凄
    0.42
    Wonderful
    0.42
    Explicit
    0.42
    Community
    0.38
    Communities
    0.37
    Gorgeous
    0.37
    Adorable
    0.36
    torrent
    0.36
    HIV
    0.34
    wonderful
    0.34
    Act Density 0.000%

    No Known Activations