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

    Neuronpedia

    INDEX
    Explanations

    recommendations or suggestions indicating the best course of action

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

    advice on best or better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.70
    AndEndTag
    -0.68
    enderror
    -0.62
     EconPapers
    -0.59
    Autoritní
    -0.54
     препратки
    -0.54
    AutoScale
    -0.51
     IBOutlet
    -0.50
    تقاوى
    -0.50
    GEBURTS
    -0.49
    POSITIVE LOGITS
     best
    0.71
     préférable
    0.69
     mejor
    0.65
    best
    0.60
     melhor
    0.59
     Best
    0.57
     Besten
    0.55
     meglio
    0.55
    lepiej
    0.54
     sebaiknya
    0.54
    Act Density 0.012%

    No Known Activations