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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and their associated metrics

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

    superlative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    躇
    -0.50
     Nacionales
    -0.45
     serpiente
    -0.44
    違った
    -0.43
     policiales
    -0.42
    脚注の使い方
    -0.41
     alluminio
    -0.41
     Infór
    -0.41
    NameInMap
    -0.41
    ñores
    -0.41
    POSITIVE LOGITS
     strongest
    0.79
     heaviest
    0.76
     hardest
    0.70
     loudest
    0.70
     widest
    0.69
     greatest
    0.68
     coldest
    0.68
     safest
    0.68
    ziest
    0.67
     highest
    0.66
    Act Density 0.183%

    No Known Activations