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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or empty tokens in the text

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

    sports teams, leagues, or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auroit
    -0.72
     avoient
    -0.65
     feroit
    -0.61
     utafitiHapana
    -0.60
     Meksika
    -0.54
     enfans
    -0.52
     Moscú
    -0.52
     étoit
    -0.52
     adquis
    -0.49
     preguntar
    -0.49
    POSITIVE LOGITS
      
    0.53
       
    0.49
    *)&
    0.48
     
    0.47
     British
    0.44
     Landis
    0.44
     IBOutlet
    0.44
    leos
    0.43
     astore
    0.43
     Local
    0.42
    Act Density 0.003%

    No Known Activations