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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to machinery and engineering processes

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

    Denotes efficiency, control, operation, or capabilities

    np_acts-logits-general · gemini-2.0-flash

    optimal performance and efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raczej
    -0.68
     EconPapers
    -0.67
     Somewhat
    -0.66
     irgendwie
    -0.66
     agak
    -0.65
     stinks
    -0.64
     jakiś
    -0.64
    あんまり
    -0.63
     Sometime
    -0.62
     trochę
    -0.62
    POSITIVE LOGITS
     unrivalled
    0.81
     optimum
    0.77
     unparalleled
    0.74
     unprecedented
    0.74
     simultaneously
    0.74
     optimal
    0.73
     efficiently
    0.73
     ensures
    0.73
     minimizes
    0.73
     optimale
    0.72
    Act Density 0.749%

    No Known Activations