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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     استخدام
    -0.07
    \Message
    -0.06
    基金
    -0.06
    禀
    -0.06
     Donation
    -0.06
     inadvertently
    -0.06
     WHETHER
    -0.06
    .osgi
    -0.06
    賦
    -0.06
    POSITIVE LOGITS
    力争
    0.07
     참여
    0.07
     Köln
    0.07
    魔
    0.07
     Cover
    0.06
     crew
    0.06
    还要
    0.06
    -detail
    0.06
     playerId
    0.06
     Receive
    0.06
    Act Density 0.001%

    No Known Activations