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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dro
    -0.07
    .drawer
    -0.06
    _merged
    -0.06
     uh
    -0.06
    keh
    -0.06
    وية
    -0.06
    虎
    -0.06
     Alam
    -0.06
    .calendar
    -0.06
    ้ไข
    -0.06
    POSITIVE LOGITS
     importante
    0.07
     belong
    0.06
    목
    0.06
     taxpayer
    0.06
     eCommerce
    0.06
    Ron
    0.06
    aliases
    0.06
    Ann
    0.06
     필
    0.06
     оттен
    0.06
    Act Density 0.000%

    No Known Activations