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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of "opening" or "accessing."

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

    open and start, new, source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.38
    inout
    -0.38
     later
    -0.33
    stre
    -0.33
    乓
    -0.33
     可
    -0.32
     verrez
    -0.32
    گاب
    -0.32
     mat
    -0.31
    บุ
    -0.31
    POSITIVE LOGITS
     propOrder
    0.65
     nakalista
    0.63
    :✨
    0.61
     EconPapers
    0.58
    INCREF
    0.56
     AttributeSet
    0.54
    __(/*!
    0.54
    OuterAlt
    0.53
    stylers
    0.53
     дописавши
    0.52
    Act Density 0.006%

    No Known Activations