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

    Neuronpedia

    INDEX
    Explanations

    references to racing or competitive events

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

    Prepositions and numbers followed by names or categories

    np_acts-logits-general · gemini-2.0-flash

    races, age groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.58
    VolleyError
    -0.57
     carico
    -0.52
     Meksiku
    -0.51
    temporada
    -0.48
    atguigu
    -0.47
     jaringan
    -0.46
     Nación
    -0.46
     mergeFrom
    -0.46
    ]=>
    -0.46
    POSITIVE LOGITS
     divisions
    0.88
     division
    0.84
    division
    0.74
    divisions
    0.71
     Divisions
    0.71
     Open
    0.70
     consolation
    0.68
     category
    0.66
     divis
    0.66
     categories
    0.66
    Act Density 0.126%

    No Known Activations