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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future events or expectations

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

    Tokens before years or numbers

    np_acts-logits-general · gemini-2.0-flash

    past dates and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.55
     препратки
    -0.51
    RTSN
    -0.51
     Abp
    -0.49
    ScopeManager
    -0.48
    lapsingToolbar
    -0.46
    uteness
    -0.46
    tagHelperRunner
    -0.46
    licone
    -0.45
     alignment
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.59
     damals
    0.56
     damaligen
    0.49
    当年
    0.46
    dealloc
    0.44
     damal
    0.42
    当時
    0.42
    当時の
    0.42
    getCell
    0.40
    batore
    0.40
    Act Density 1.347%

    No Known Activations