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

    Neuronpedia

    INDEX
    Explanations

    to the that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulner
    -0.06
    \/
    -0.06
     склад
    -0.06
    "]
    -0.06
    	at
    -0.06
    约
    -0.06
    imit
    -0.06
     máximo
    -0.06
     weed
    -0.05
     say
    -0.05
    POSITIVE LOGITS
    Poster
    0.07
     cum
    0.07
    -ip
    0.06
     م
    0.06
     classmates
    0.06
    연구
    0.06
     CELL
    0.06
    .Span
    0.06
    .gwt
    0.06
     ود
    0.06
    Act Density 0.047%

    No Known Activations