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

    Neuronpedia

    INDEX
    Explanations

    User-generated content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oku
    -0.07
     Hyper
    -0.06
    anced
    -0.06
    magic
    -0.06
    urance
    -0.06
     함
    -0.06
     primarily
    -0.06
    行
    -0.06
     stays
    -0.06
     invitation
    -0.06
    POSITIVE LOGITS
    ……」↵↵
    0.06
    چی
    0.06
     Farrell
    0.06
     akşam
    0.06
    <My
    0.06
    ву
    0.06
     ilma
    0.06
     zh
    0.06
     منها
    0.06
     đêm
    0.06
    Act Density 0.223%

    No Known Activations