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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation indicative of mathematical expressions or programming syntax

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

    "e.g.", "i.e.", "think"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ?>/
    -0.36
    ])).
    -0.34
    ]|
    -0.33
    ])+
    -0.33
     er
    -0.33
     sob
    -0.33
    __((
    -0.32
    }}=
    -0.32
     ru
    -0.32
    答
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.80
    :✨
    0.72
     termica
    0.70
    PostInfinity
    0.62
     disponibilités
    0.62
     HasFactory
    0.61
     للاسماء
    0.60
     picioare
    0.59
    matchCondition
    0.58
     queſta
    0.57
    Act Density 0.220%

    No Known Activations