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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditional relationships or comparisons

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

    however, the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.55
    RNG
    -0.53
    رشف
    -0.53
    舺
    -0.53
    ロウィン
    -0.52
    <unused32>
    -0.52
     EconPapers
    -0.52
    <unused47>
    -0.51
     متعلقه
    -0.51
     plait
    -0.51
    POSITIVE LOGITS
     uzak
    0.35
     mystère
    0.35
     kæ
    0.35
     linkovi
    0.34
    deki
    0.33
     tatuagens
    0.32
     much
    0.32
    setVerticalGroup
    0.31
    altezza
    0.31
     noget
    0.31
    Act Density 0.100%

    No Known Activations