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

    Neuronpedia

    INDEX
    Explanations

    structure and syntax in programming code

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

    Code, math, or uncommon words

    np_acts-logits-general · gemini-2.0-flash

    code and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.72
     the
    -0.59
     pure
    -0.58
     cross
    -0.53
    aarrggbb
    -0.53
     (
    -0.53
    ,
    -0.53
     above
    -0.53
    -
    -0.51
     B
    -0.51
    POSITIVE LOGITS
     MonoBehaviour
    0.87
    GEBURTSDATUM
    0.83
     fubject
    0.78
     Whigs
    0.76
     myſelf
    0.74
    存于互联网档案馆
    0.74
     itſelf
    0.72
     abstrato
    0.71
     impea
    0.71
     Houſe
    0.70
    Act Density 0.095%

    No Known Activations