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

    Neuronpedia

    INDEX
    Explanations

    numbers and their formatting, possibly in relation to dates or records

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

    Dashes followed by timestamps

    np_acts-logits-general · gemini-2.0-flash

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.53
    <?
    -0.49
    bootstrapcdn
    -0.48
    发表于
    -0.47
     nahilalakip
    -0.46
     Originals
    -0.45
     pos
    -0.44
    ze
    -0.44
     Introducing
    -0.43
     introduce
    -0.43
    POSITIVE LOGITS
     препратки
    0.74
     Numerade
    0.69
    endphp
    0.61
     raiſ
    0.59
    Filmographie
    0.59
    BeginContext
    0.59
     متعلقه
    0.59
     CommonModule
    0.59
    Décès
    0.59
     myſelf
    0.58
    Act Density 0.142%

    No Known Activations