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

    Neuronpedia

    INDEX
    Explanations

    references to global or societal contexts

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

    world, country, nation, society, campus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.49
     represent
    -0.39
    ましい
    -0.39
    原始内容存档于
    -0.38
     instru
    -0.37
    addCriterion
    -0.37
     Represent
    -0.36
     <<<<<<<<<<<<<<
    -0.35
    explained
    -0.35
     represents
    -0.35
    POSITIVE LOGITS
     collectively
    0.87
     entière
    0.57
     kennis
    0.57
     unanimously
    0.56
     collective
    0.55
     inteiro
    0.53
     learns
    0.52
     rallied
    0.52
     anxiously
    0.50
     impatiently
    0.50
    Act Density 0.062%

    No Known Activations