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

    Neuronpedia

    INDEX
    Explanations

    keys, values, four, one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     star
    0.80
     transaction
    0.77
     rho
    0.75
     ray
    0.73
     bee
    0.72
    াচিত
    0.72
     rays
    0.71
     brook
    0.70
    ર્ડ
    0.69
     sperm
    0.68
    POSITIVE LOGITS
    Monkey
    0.80
    지난
    0.75
    вете
    0.74
    激动
    0.74
    ﺃ
    0.74
    いずれ
    0.73
    tfidf
    0.72
     ограни
    0.71
    一定要
    0.71
    یا
    0.71
    Act Density 0.005%

    No Known Activations