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

    Neuronpedia

    INDEX
    Explanations

    patterns of repeated or duplicated characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Jamestown, quotes, code, rendering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.64
     feroit
    -0.56
     desmotivaciones
    -0.56
     république
    -0.51
    colgante
    -0.51
    calça
    -0.50
    Mitä
    -0.50
     wikipagina
    -0.50
     dignité
    -0.50
     pouvoit
    -0.50
    POSITIVE LOGITS
      
    0.70
       
    0.56
     kasarigan
    0.56
      
    0.50
    WriteLiteral
    0.50
     
    0.47
    displayquote
    0.47
     Jamestown
    0.46
     Taktlose
    0.46
    ImageContext
    0.45
    Act Density 0.000%

    No Known Activations