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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements or conflicts in various contexts

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

    verbs followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.54
    Tembelea
    -0.44
     gyhoeddwyd
    -0.40
    页面存档备份
    -0.38
    parseColor
    -0.38
    WebControls
    -0.38
    Slf
    -0.38
    makeConstraints
    -0.37
     keineswegs
    -0.37
    ransition
    -0.37
    POSITIVE LOGITS
    featureID
    0.56
    ViewImports
    0.48
    ScopeManager
    0.47
    zeera
    0.44
     eux
    0.44
    findpost
    0.43
    \{\\
    0.43
     AssemblyProduct
    0.42
    /**
    0.41
    :^{
    0.40
    Act Density 0.136%

    No Known Activations