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

    Neuronpedia

    INDEX
    Explanations

    references to rankings or hierarchical positions

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

    Tokens followed by "rank"

    np_acts-logits-general · gemini-2.0-flash

    rank order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.57
    FML
    -0.49
    bB
    -0.48
    YesNo
    -0.47
    /*
    -0.47
    ように
    -0.46
    ⎩
    -0.46
     endTime
    -0.45
     esternos
    -0.45
    ओं
    -0.45
    POSITIVE LOGITS
    قایناقلار
    0.90
     RANK
    0.84
    Personendaten
    0.82
    RANK
    0.77
    :✨
    0.76
    BlockingQueue
    0.71
     Ranks
    0.70
     ranks
    0.69
     Rank
    0.69
    Rank
    0.69
    Act Density 0.084%

    No Known Activations