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

    Neuronpedia

    INDEX
    Explanations

    stop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     tương
    -0.07
    温泉
    -0.07
     chaud
    -0.07
    ⵢ
    -0.07
    佺
    -0.07
    贴
    -0.07
    🇶
    -0.07
    辅导
    -0.07
    (visible
    -0.07
    POSITIVE LOGITS
     stop
    0.08
    StringRef
    0.08
     не
    0.07
     Jak
    0.07
    Ar
    0.07
    请点击
    0.07
    rm
    0.07
     SF
    0.07
     disemb
    0.07
    一些
    0.07
    Act Density 0.030%

    No Known Activations