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

    Neuronpedia

    INDEX
    Explanations

    the concept of "two" in various contexts, indicating relationships or categorizations

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

    "two"

    np_acts-logits-general · gemini-2.0-flash

    two types or ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.87
     himſelf
    -0.85
     Jefus
    -0.81
     myſelf
    -0.81
     Efq
    -0.81
     themſelves
    -0.79
     houſe
    -0.75
     ſtate
    -0.75
     whoſe
    -0.74
     Eſ
    -0.74
    POSITIVE LOGITS
     halves
    0.72
     main
    0.71
     pinulongan
    0.65
     two
    0.64
     big
    0.64
    NameInMap
    0.64
     GenerationType
    0.63
    uttgart
    0.61
    RTLD
    0.61
     CWE
    0.60
    Act Density 0.302%

    No Known Activations