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

    Neuronpedia

    INDEX
    Explanations

    references to documents, guides, or notes related to discussions or summaries

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

    report summary notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.68
    tagHelperRunner
    -0.66
    addContainerGap
    -0.58
     Normdatei
    -0.54
    TagMode
    -0.53
    medriver
    -0.53
    Personensuche
    -0.52
    IntoConstraints
    -0.52
    GEBURTS
    -0.51
    GRANTED
    -0.51
    POSITIVE LOGITS
    FunctionFlags
    0.37
     summary
    0.35
     summaries
    0.34
     reported
    0.33
     report
    0.32
     antaranya
    0.32
    ésultat
    0.32
    report
    0.32
     descriptions
    0.31
    description
    0.31
    Act Density 0.109%

    No Known Activations