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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    企
    -0.06
     ainda
    -0.06
    ただ
    -0.06
    �情
    -0.06
     effectively
    -0.06
     compet
    -0.06
    rame
    -0.06
     Governments
    -0.06
    меч
    -0.06
    uplicates
    -0.06
    POSITIVE LOGITS
    ]<<"
    0.07
    تهم
    0.07
    )}</
    0.07
    -focus
    0.06
    Classic
    0.06
     Breaking
    0.06
    щается
    0.06
    tuk
    0.06
     ＼↵
    0.06
     barbecue
    0.06
    Act Density 0.000%

    No Known Activations