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

    Neuronpedia

    INDEX
    Explanations

    high-frequency numerical values

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

    seventeen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astéro
    -0.58
    ServletConfig
    -0.57
     Siddi
    -0.51
    obot
    -0.51
    consul
    -0.50
     Groove
    -0.50
    Hund
    -0.50
    Schwe
    -0.50
     iprot
    -0.49
     Roskov
    -0.49
    POSITIVE LOGITS
     seventeen
    0.65
     seventeenth
    0.64
    XVII
    0.60
     xvii
    0.59
     Seventeen
    0.59
     XVII
    0.55
     Seventeenth
    0.54
     ۱۷
    0.53
    EEN
    0.51
    xvii
    0.50
    Act Density 0.076%

    No Known Activations