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

    Neuronpedia

    INDEX
    Explanations

    unusual text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中医
    -0.07
    孕妇
    -0.07
     compass
    -0.07
     badań
    -0.06
     Wander
    -0.06
     đồ
    -0.06
     GENER
    -0.06
    مجموع
    -0.06
    URN
    -0.06
    nav
    -0.06
    POSITIVE LOGITS
     hiếm
    0.08
     preservation
    0.08
    !=
    0.07
    ietet
    0.07
    ฉาก
    0.07
    的传统
    0.07
     rooting
    0.07
    ---
↵
    0.07
    _sh
    0.07
    쏟
    0.07
    Act Density 0.000%

    No Known Activations