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

    Neuronpedia

    INDEX
    Explanations

    references to names and their recognition in various contexts

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

    remembering names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.61
    parsedMessage
    -0.52
    contentLoaded
    -0.45
     Audiodateien
    -0.42
    nup
    -0.40
     vPvB
    -0.40
    oneofs
    -0.40
    ApiModelProperty
    -0.40
    volante
    -0.39
     iconTwitter
    -0.39
    POSITIVE LOGITS
     memorize
    0.57
     Knowing
    0.54
    Familiar
    0.52
     familiarize
    0.51
     familiar
    0.51
    knowing
    0.50
    Knowing
    0.49
     memorized
    0.49
     knowing
    0.49
     Familiar
    0.49
    Act Density 0.034%

    No Known Activations