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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    одейств
    -0.06
     recognizes
    -0.06
     republika
    -0.06
     gần
    -0.06
     dataType
    -0.06
     pooling
    -0.06
    服
    -0.06
    نز
    -0.06
    小说
    -0.06
    监督
    -0.06
    POSITIVE LOGITS
    ickers
    0.07
     insults
    0.07
     inmate
    0.07
    Clicked
    0.07
    	Start
    0.06
    Tyler
    0.06
    CX
    0.06
    (Media
    0.06
     Comment
    0.06
    Never
    0.06
    Act Density 0.018%

    No Known Activations