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

    Neuronpedia

    INDEX
    Explanations

    Mixed, technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    욛
    -0.08
    mayı
    -0.07
    🙋
    -0.07
     Qin
    -0.07
     hentai
    -0.07
    캠
    -0.07
     Santos
    -0.07
     ödül
    -0.07
    July
    -0.07
    aryl
    -0.07
    POSITIVE LOGITS
    相符
    0.08
     removeFromSuperview
    0.08
     riêng
    0.07
    纤维
    0.07
     الداخلية
    0.07
    金融
    0.07
    What
    0.07
    -fr
    0.07
    _concat
    0.07
    Opt
    0.07
    Act Density 0.345%

    No Known Activations