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

    Neuronpedia

    INDEX
    Explanations

    phrases that quantify excellence or superiority in various contexts

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

    best of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coroa
    -0.46
     bandeira
    -0.45
    nyataan
    -0.44
     camiset
    -0.43
     frågan
    -0.42
     which
    -0.42
     violación
    -0.41
     noiva
    -0.40
    hilangan
    -0.39
     cuánt
    -0.39
    POSITIVE LOGITS
    Best
    0.91
    best
    0.90
     BEST
    0.90
    BEST
    0.88
     best
    0.87
     Best
    0.85
    worst
    0.78
    Better
    0.76
     terbaik
    0.76
     Better
    0.74
    Act Density 0.022%

    No Known Activations