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

    Neuronpedia

    INDEX
    Explanations

    %)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Interaction
    -0.07
    plib
    -0.07
     party
    -0.07
     정규
    -0.06
     toxin
    -0.06
    -product
    -0.06
    _threads
    -0.06
     repo
    -0.06
     คำ
    -0.06
    伯
    -0.06
    POSITIVE LOGITS
     GestureDetector
    0.08
     атмос
    0.07
     тогда
    0.07
     ним
    0.07
     Зах
    0.07
    耶
    0.07
    こちら
    0.07
    (CC
    0.07
     NSK
    0.06
     Кри
    0.06
    Act Density 0.019%

    No Known Activations