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

    Neuronpedia

    INDEX
    Explanations

    HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ercise
    -0.08
     erfahren
    -0.07
     sources
    -0.07
     fork
    -0.07
     forks
    -0.06
     bại
    -0.06
    ابة
    -0.06
     website
    -0.06
    esco
    -0.06
     cycle
    -0.06
    POSITIVE LOGITS
    orthand
    0.06
    &m
    0.06
     hạn
    0.06
     Blo
    0.06
    тор
    0.06
     Boca
    0.06
    expr
    0.06
    	loc
    0.06
    .tap
    0.06
     Pets
    0.06
    Act Density 0.010%

    No Known Activations