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

    Neuronpedia

    INDEX
    Explanations

    instances of research-related jargon and terminology

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

    code markers, citations, and foreign scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⤹
    -0.56
     Chambers
    -0.55
     Sax
    -0.53
     Bas
    -0.52
     setShow
    -0.51
    ornment
    -0.50
     Schrader
    -0.50
     soggior
    -0.50
     Victory
    -0.49
    uestamente
    -0.48
    POSITIVE LOGITS
    存于互联网档案馆
    0.47
    tagHelperRunner
    0.42
    __*/
    0.41
     nahilalakip
    0.36
    ล้ว
    0.35
     đều
    0.35
    endphp
    0.31
     сериала
    0.30
    dersfield
    0.29
    /*
    0.29
    Act Density 0.005%

    No Known Activations