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

    Neuronpedia

    INDEX
    Explanations

    assertions of excellence and high quality in various contexts

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

    positive descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bigger
    -0.52
    sterious
    -0.50
     funnier
    -0.47
     big
    -0.42
    bigger
    -0.42
     softer
    -0.41
     wetter
    -0.41
     biggest
    -0.40
    Biggest
    -0.40
     BIG
    -0.39
    POSITIVE LOGITS
     Excellent
    1.16
    Excellent
    1.16
     excellent
    1.14
    excellent
    1.11
     excelentes
    1.01
     excelente
    0.98
    excelente
    0.95
     eccellente
    0.94
     excellente
    0.91
    excell
    0.91
    Act Density 0.018%

    No Known Activations