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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zoals
    -0.07
    raf
    -0.07
    ré
    -0.07
    р
    -0.06
    ne
    -0.06
     [:
    -0.06
     tren
    -0.06
     Por
    -0.06
     Andreas
    -0.06
     grenades
    -0.06
    POSITIVE LOGITS
     HomeComponent
    0.07
    IEL
    0.06
     امتی
    0.06
     　　　　　　　　
    0.06
    Groups
    0.06
     Reminder
    0.06
     [],↵
    0.06
    اگ
    0.06
     Worm
    0.06
    DataBase
    0.06
    Act Density 0.050%

    No Known Activations