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

    Neuronpedia

    INDEX
    Explanations

    transition words and phrases indicating conclusions or summaries

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

    so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.50
     vPvB
    -0.49
    :+:
    -0.46
    invokeLater
    -0.46
     newOwner
    -0.44
    PDATE
    -0.44
    GTCX
    -0.43
    ResumeLayout
    -0.43
     defaultstate
    -0.41
    SourceChecksum
    -0.41
    POSITIVE LOGITS
    brigens
    0.57
    Quindi
    0.54
    libatkan
    0.54
    Clearly
    0.54
     Hälfte
    0.52
     Padova
    0.51
    Definitely
    0.51
     takže
    0.50
     Dlatego
    0.50
     alltså
    0.50
    Act Density 0.054%

    No Known Activations