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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal documentation and their structure

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

    Comes before a colon

    np_acts-logits-general · gemini-2.0-flash

    " August" or "What" following "."

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.97
    principalColumn
    -0.81
     للمعارف
    -0.81
    Diweddarwch
    -0.79
     '\\;'
    -0.78
    EndInit
    -0.78
    Personensuche
    -0.77
     للاسماء
    -0.75
    Hentet
    -0.75
     AssemblyCulture
    -0.75
    POSITIVE LOGITS
    The
    0.50
    Please
    0.48
    Key
    0.46
    Note
    0.46
    https
    0.46
    http
    0.45
    Why
    0.45
    For
    0.44
    Any
    0.43
    This
    0.42
    Act Density 0.387%

    No Known Activations