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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or quotation characters

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

    file open/close operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.70
    PerformLayout
    -0.60
    :✨
    -0.60
    uxxxx
    -0.59
    SBATCH
    -0.54
    GEBURTSDATUM
    -0.54
    InstrumentedTest
    -0.52
     contextLoads
    -0.52
     дописавши
    -0.52
     समीक्षाओं
    -0.52
    POSITIVE LOGITS
    ituary
    0.42
    getApplication
    0.38
     Franks
    0.38
     open
    0.37
     marbre
    0.37
    AutoField
    0.36
     cuivre
    0.36
     Spiegel
    0.35
     diamants
    0.35
     forState
    0.35
    Act Density 0.003%

    No Known Activations