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

    Neuronpedia

    INDEX
    Explanations

    references to memory and its significance

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

    memory and remembrance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extendable
    -0.40
    AndEndTag
    -0.37
    ended
    -0.35
     mû
    -0.34
    Consumer
    -0.33
    cedentes
    -0.33
    anguages
    -0.32
    [[
    -0.32
    sunter
    -0.32
    sor
    -0.31
    POSITIVE LOGITS
     memory
    0.96
     Memory
    0.91
     MEMORY
    0.82
    memory
    0.77
    Memory
    0.77
     memória
    0.75
     remembrance
    0.74
     memoria
    0.72
    Décès
    0.69
    メモリ
    0.69
    Act Density 0.001%

    No Known Activations