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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    䝙
    -0.08
    zones
    -0.07
    .”↵↵↵↵
    -0.07
    參加
    -0.07
    單位
    -0.07
    Coach
    -0.07
    aud
    -0.07
     offic
    -0.06
    ogn
    -0.06
    assuming
    -0.06
    POSITIVE LOGITS
    \xaa
    0.07
     yüz
    0.07
    了好多
    0.07
    播报
    0.07
     Guardians
    0.07
    ')->__('
    0.07
    许多
    0.07
    约谈
    0.06
    眊
    0.06
    맊
    0.06
    Act Density 0.004%

    No Known Activations