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
     peng
    -0.07
    >Select
    -0.06
     Interior
    -0.06
    ’m
    -0.06
    Lastly
    -0.06
    Usage
    -0.06
    	This
    -0.06
    "M
    -0.06
     Tex
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _NAME
    0.07
    กลาง
    0.06
    包含
    0.06
    ッカー
    0.06
     bron
    0.06
     valida
    0.06
    hoot
    0.06
     هی
    0.06
     forIndexPath
    0.06
    وقت
    0.06
    Act Density 0.005%

    No Known Activations