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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glare
    -0.07
     nada
    -0.06
    Protect
    -0.06
    _FILL
    -0.06
    ，与
    -0.06
     Olympia
    -0.06
    stime
    -0.06
    数据库
    -0.06
    urar
    -0.06
    aub
    -0.06
    POSITIVE LOGITS
     Ago
    0.07
    .Strings
    0.06
    -hooks
    0.06
    ModelProperty
    0.06
    Techn
    0.06
    colors
    0.06
     supporter
    0.06
     mural
    0.06
    Ing
    0.06
    (tt
    0.06
    Act Density 0.002%

    No Known Activations