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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating ongoing relevance or continuity

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

    Something that is still around

    np_acts-logits-general · gemini-2.0-flash

    still and retains status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    already
    -1.10
     already
    -1.05
    Already
    -1.01
     Already
    -1.00
    出版年
    -0.98
     suddenly
    -0.96
     ALREADY
    -0.94
    again
    -0.93
    ftagPool
    -0.93
    IndentedString
    -0.90
    POSITIVE LOGITS
     intact
    0.77
     remains
    0.62
     relevant
    0.60
     alive
    0.58
     valid
    0.58
     retains
    0.54
    væ
    0.54
    現役
    0.53
     remain
    0.51
     viable
    0.51
    Act Density 0.215%

    No Known Activations