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

    Neuronpedia

    INDEX
    Explanations

    ignore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subsets
    -0.07
    ushi
    -0.07
    ero
    -0.07
     сочета
    -0.07
     נכונה
    -0.07
    unch
    -0.06
    _MOVE
    -0.06
    淑
    -0.06
    出来了
    -0.06
    Customers
    -0.06
    POSITIVE LOGITS
    貆
    0.08
    萘
    0.07
     and
    0.07
     н
    0.07
    (priv
    0.06
    揩
    0.06
     menggunakan
    0.06
     Ign
    0.06
     процент
    0.06
    reinterpret
    0.06
    Act Density 0.016%

    No Known Activations