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

    Neuronpedia

    INDEX
    Explanations

    Legal acts and laws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tv
    -0.08
    粲
    -0.08
    最爱
    -0.07
    .ll
    -0.07
     dairy
    -0.07
    ]);
↵
↵
    -0.07
     месяцев
    -0.07
    	cm
    -0.07
    那是
    -0.07
     cares
    -0.06
    POSITIVE LOGITS
    omb
    0.07
     unge
    0.07
     recruited
    0.07
     commerc
    0.07
    ometown
    0.07
    orget
    0.07
    ロン
    0.07
    ращ
    0.06
     inward
    0.06
    旋转
    0.06
    Act Density 0.009%

    No Known Activations