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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and code structure elements

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.74
    tonsoft
    -0.69
    нгред
    -0.61
     MainAxisSize
    -0.60
     Exacts
    -0.59
    ésultats
    -0.59
    AddTagHelper
    -0.58
     laſſen
    -0.58
    Хьажоргаш
    -0.57
    RegressionTest
    -0.57
    POSITIVE LOGITS
     ALREADY
    0.40
    <eos>
    0.39
    ALREADY
    0.38
     already
    0.35
     IS
    0.35
    pad
    0.34
     tässä
    0.33
    imbang
    0.32
     pad
    0.32
     siinä
    0.32
    Act Density 0.013%

    No Known Activations