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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and organizations

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

    family, brotherhood

    np_max-act-logits · gemini-2.0-flashTriggered by @arientigiacomo2003
    New Auto-Interp
    Negative Logits
    SpringRunner
    -0.57
    styleUrls
    -0.55
    ResponseWriter
    -0.54
    RSpec
    -0.53
    tences
    -0.53
    每个人
    -0.51
    Jeografia
    -0.51
    XMLSchema
    -0.49
    حياته
    -0.48
    antaine
    -0.46
    POSITIVE LOGITS
     Brothers
    0.96
     brothers
    0.91
     frères
    0.85
     family
    0.81
     Bros
    0.81
     Family
    0.79
     család
    0.78
    brothers
    0.77
    Brothers
    0.77
     BROTHERS
    0.77
    Act Density 0.736%

    No Known Activations