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

    Neuronpedia

    INDEX
    Explanations

    terms related to documentation and manuscripts

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

    ending in "es" or "ses"

    np_acts-logits-general · gemini-2.0-flash

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orteur
    -0.83
    NOPQRST
    -0.74
     pleaſure
    -0.72
     estekak
    -0.71
    toire
    -0.71
    iencing
    -0.71
     Baillargeon
    -0.70
     Administrativna
    -0.70
    skyl
    -0.69
    -0.69
    POSITIVE LOGITS
    es
    1.15
    ses
    1.03
    ES
    1.00
    ness
    0.88
    NESS
    0.84
    nes
    0.84
    aS
    0.84
     Tres
    0.80
     Bass
    0.80
    mos
    0.79
    Act Density 1.187%

    No Known Activations