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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and personal fulfillment

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

    years and career accomplishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    三日
    -0.54
     customise
    -0.52
     halloween
    -0.47
     Cupcake
    -0.47
    :✨
    -0.46
     للاسماء
    -0.45
    tubers
    -0.43
    AlterField
    -0.43
    hype
    -0.43
     newbies
    -0.43
    POSITIVE LOGITS
     åren
    0.64
    SequentialGroup
    0.61
     decades
    0.60
     nikdy
    0.59
     carriera
    0.59
     career
    0.59
     années
    0.58
     carrière
    0.56
     maisha
    0.54
     årene
    0.54
    Act Density 0.034%

    No Known Activations