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

    Neuronpedia

    INDEX
    Explanations

    clay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     negate
    -0.08
    מ
    -0.07
    �
    -0.07
     özgü
    -0.07
    �
    -0.07
    �
    -0.07
     sensations
    -0.07
    �
    -0.07
    �
    -0.07
    ご�
    -0.07
    POSITIVE LOGITS
    烟台
    0.08
     FAA
    0.08
    物业公司
    0.07
    دفاع
    0.07
    wget
    0.07
     Halo
    0.07
    에너
    0.07
     CCP
    0.07
     الحالي
    0.07
    北约
    0.07
    Act Density 0.002%

    No Known Activations