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

    Neuronpedia

    INDEX
    Explanations

    mathematical roots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ballroom
    -0.08
     butterflies
    -0.08
     flutter
    -0.08
    Butter
    -0.07
    fatt
    -0.07
     especializada
    -0.07
     शुरुआत
    -0.07
    andre
    -0.07
    osia
    -0.07
    utele
    -0.07
    POSITIVE LOGITS
    三个
    0.13
     cubic
    0.12
     మూడు
    0.11
     তিন
    0.11
     三
    0.11
    ³
    0.11
     മൂന്ന്
    0.10
     trei
    0.10
     ત્રણ
    0.10
     үш
    0.10
    Act Density 0.064%

    No Known Activations