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

    Neuronpedia

    INDEX
    Explanations

    timestamps and numerical data

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

    Dates with numbers

    np_acts-logits-general · gemini-2.0-flash

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dec
    -0.51
     mode
    -0.51
     er
    -0.49
     cada
    -0.47
     n
    -0.47
     Nov
    -0.47
     on
    -0.47
     Er
    -0.47
     Oct
    -0.45
     modes
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.94
    rungsseite
    0.91
     MainAxisSize
    0.88
     архивлан
    0.88
     uſed
    0.87
    PhysRevD
    0.84
     myſelf
    0.82
     itſelf
    0.81
    SourceChecksum
    0.81
     afternoon
    0.81
    Act Density 0.154%

    No Known Activations