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

    Neuronpedia

    INDEX
    Explanations

    Region

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     době
    -0.06
            ↵        ↵        ↵
    -0.06
    ують
    -0.06
     있다
    -0.05
    oč
    -0.05
     CRA
    -0.05
    .assertj
    -0.05
    ]);
↵
↵
    -0.05
     paced
    -0.05
    除了
    -0.05
    POSITIVE LOGITS
     Local
    0.07
     NOI
    0.07
     london
    0.07
    厂
    0.07
     local
    0.06
    .Toggle
    0.06
     prank
    0.06
    _dn
    0.06
    сі
    0.06
    .nama
    0.06
    Act Density 0.002%

    No Known Activations