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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <=>
    -0.08
    ╟
    -0.07
    嚏
    -0.07
    릅
    -0.07
    מכון
    -0.07
    STYLE
    -0.07
    틑
    -0.07
     Modify
    -0.06
    	Created
    -0.06
     הבית
    -0.06
    POSITIVE LOGITS
     الجديدة
    0.08
    _enter
    0.07
    oin
    0.07
    쩠
    0.07
    Runnable
    0.07
     Hak
    0.07
    航
    0.07
    Emergency
    0.07
    ➿
    0.07
    embre
    0.07
    Act Density 0.001%

    No Known Activations