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

    Neuronpedia

    INDEX
    Explanations

    function definitions and return statements in code

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

    programming language types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.71
    RegressionTest
    -0.57
    Rüyada
    -0.55
     forfait
    -0.51
    fjspx
    -0.50
    transQ
    -0.49
    fromnode
    -0.48
    endaten
    -0.48
     gethan
    -0.47
     Monfieur
    -0.47
    POSITIVE LOGITS
    mtrl
    0.46
     ujednoznacz
    0.43
    WriteTagHelper
    0.39
    Билгалдахарш
    0.36
    AddTagHelper
    0.35
     AssemblyCulture
    0.34
     orgánico
    0.34
    кобрита
    0.33
     مرئيه
    0.33
     vectoriales
    0.32
    Act Density 0.001%

    No Known Activations