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

    Neuronpedia

    INDEX
    Explanations

    references to specific events, locations, and dates

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

    Tokens preceding decimals, prices, or numbers

    np_acts-logits-general · gemini-2.0-flash

    .com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rumors
    -0.78
     Rumors
    -0.77
     Utilizing
    -0.76
    Rumors
    -0.72
     rumor
    -0.69
     utilizing
    -0.69
    исленность
    -0.66
     utilize
    -0.65
     harbor
    -0.64
     Savior
    -0.64
    POSITIVE LOGITS
     realising
    0.65
     stabilisation
    0.64
     realises
    0.63
     realised
    0.62
     Nato
    0.62
     Bucure
    0.61
     crystall
    0.59
    ●
    0.57
     realise
    0.57
    ✱
    0.57
    Act Density 0.113%

    No Known Activations