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

    Neuronpedia

    INDEX
    Explanations

    Reasoning, purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (:,:,
    -0.08
     aand
    -0.07
     Tai
    -0.07
     Tip
    -0.07
     million
    -0.07
     giga
    -0.07
    �
    -0.07
     details
    -0.07
    الث
    -0.07
     Dong
    -0.07
    POSITIVE LOGITS
     উদ্দেশ
    0.10
     목적
    0.10
    目的
    0.10
     justement
    0.09
    olvers
    0.09
     Zweck
    0.09
     उद्देश्य
    0.09
    ULO
    0.09
    หลัก
    0.09
    대로
    0.09
    Act Density 0.102%

    No Known Activations