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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     쇼
    -0.07
     مات
    -0.07
    packageName
    -0.07
    onChange
    -0.07
     Este
    -0.06
    >'
    -0.06
    	CHECK
    -0.06
    乾
    -0.06
    _LIBRARY
    -0.06
    كر
    -0.06
    POSITIVE LOGITS
     annual
    0.08
     výrob
    0.07
     mamm
    0.07
    Former
    0.07
    �
    0.06
    .tw
    0.06
    ुप
    0.06
    /int
    0.06
     butterflies
    0.06
    ymm
    0.06
    Act Density 0.026%

    No Known Activations