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

    Neuronpedia

    INDEX
    Explanations

    coding-related syntax errors and practices

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

    code artifacts, URLs, or data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelState
    -0.43
     catalog
    -0.40
    刻
    -0.39
     recordings
    -0.39
    aspectj
    -0.38
     reputation
    -0.38
     fus
    -0.37
     themes
    -0.36
    delaire
    -0.36
     catalogue
    -0.36
    POSITIVE LOGITS
    帖最后由
    0.68
     newOwner
    0.59
    GOTREF
    0.54
    PerformLayout
    0.52
     instead
    0.52
    AnchorTagHelper
    0.51
    instead
    0.50
     beroep
    0.50
    irvana
    0.49
     AssemblyProduct
    0.49
    Act Density 0.143%

    No Known Activations