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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations or companies and their associated terms

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

    sum and dim sum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fragile
    -0.39
    ,
    -0.39
    ↵↵
    -0.38
    ↵
    -0.38
     precious
    -0.37
     bitter
    -0.36
     sensitive
    -0.36
     mouse
    -0.36
     Class
    -0.35
     relatively
    -0.35
    POSITIVE LOGITS
     AssemblyCompany
    1.64
    الدراسه
    1.28
     surla
    1.17
    ValueStyle
    1.12
    cipar
    1.10
    tagHelperRunner
    1.07
    atguigu
    0.96
    mapreduce
    0.93
    ✨:
    0.89
    Tikang
    0.88
    Act Density 0.008%

    No Known Activations