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

    Neuronpedia

    INDEX
    Explanations

    specific LaTeX formatting commands related to document structure

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

    user input contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tensors
    -0.35
    可是
    -0.33
    กรม
    -0.33
    бият
    -0.33
     AssemblyCompany
    -0.32
    劲
    -0.32
    不着
    -0.32
    řevě
    -0.31
     elder
    -0.31
    cvtColor
    -0.31
    POSITIVE LOGITS
    multirow
    0.67
    WebElementEntity
    0.64
    tagHelperRunner
    0.62
     ProtoMessage
    0.61
    ContentAsync
    0.60
    enterOuterAlt
    0.56
    0.56
     AssemblyCulture
    0.55
    complexContent
    0.53
    })$}
    0.53
    Act Density 0.002%

    No Known Activations