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

    Neuronpedia

    INDEX
    Explanations

    the presence of the start of a document

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

    "we", "us", "you", or "I"

    np_acts-logits-general · gemini-2.0-flash

    pronouns and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✨:
    -0.92
    jspb
    -0.79
     '\\;'
    -0.77
    :✨
    -0.73
    ()?;
    -0.70
    oredCriteria
    -0.69
    -0.67
    Jereo
    -0.66
     seemingly
    -0.64
     Meksiku
    -0.64
    POSITIVE LOGITS
     ourselves
    0.68
     we
    0.66
     We
    0.65
     I
    0.64
     our
    0.63
     [
    0.59
     whatever
    0.58
     you
    0.58
     myself
    0.57
     people
    0.57
    Act Density 0.056%

    No Known Activations