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

    Neuronpedia

    INDEX
    Explanations

    irony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ;;=
    -0.07
     לו
    -0.07
    烟囱
    -0.07
    邮轮
    -0.07
     المشترك
    -0.07
    魔龙令牌
    -0.07
    ﱃ
    -0.07
     compra
    -0.07
     &,
    -0.06
    みて
    -0.06
    POSITIVE LOGITS
     Aub
    0.08
     Prob
    0.07
    执政
    0.07
    illas
    0.07
    ucle
    0.07
    Table
    0.07
     initiative
    0.07
    भ
    0.07
     прав
    0.07
    -Ch
    0.07
    Act Density 0.064%

    No Known Activations