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

    Neuronpedia

    INDEX
    Explanations

    instances of unreadable or encoded strings and email addresses

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

    citations omitted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colgante
    -0.54
     mecánico
    -0.46
     campamento
    -0.46
     flota
    -0.44
     romántico
    -0.44
     Keuangan
    -0.43
     sellado
    -0.43
     pérd
    -0.43
     habitudes
    -0.42
     Jehová
    -0.41
    POSITIVE LOGITS
     оригіналу
    0.59
    脚注の使い方
    0.57
    󠁢
    0.57
     Armor
    0.54
     {?}
    0.51
     SND
    0.51
     SHIELD
    0.50
    snip
    0.50
    󠁧
    0.50
     HttpNotFound
    0.50
    Act Density 0.499%

    No Known Activations