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

    Neuronpedia

    INDEX
    Explanations

    terms related to performance metrics and evaluation in a computational context

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

    ELF simple descriptors, splines, pixels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étoit
    -0.33
     persoonlijke
    -0.29
     gezond
    -0.27
    esercito
    -0.26
    enschappe
    -0.26
     
    -0.26
     gezondheid
    -0.26
     CONS
    -0.25
    Gizmos
    -0.25
     derfor
    -0.25
    POSITIVE LOGITS
    fromnode
    0.66
    :✨
    0.65
    transQ
    0.64
     חיצוניים
    0.62
     вікісторінку
    0.62
     &___
    0.59
     unfold
    0.58
    styleType
    0.56
    ValueStyle
    0.56
     unfolds
    0.56
    Act Density 0.775%

    No Known Activations