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

    Neuronpedia

    INDEX
    Explanations

    formatted attributes or highlights in a scientific context, especially those denoted by asterisks or bold formatting

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

    bolded or asterisked items followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pères
    -0.61
     zoude
    -0.60
    ientras
    -0.59
     zelve
    -0.59
     wikipagina
    -0.59
     Monfieur
    -0.59
     plufieurs
    -0.58
    Personendaten
    -0.57
     enfans
    -0.56
     Cæsar
    -0.55
    POSITIVE LOGITS
    </h4>
    0.39
     thereby
    0.35
     Đ
    0.32
     potentially
    0.32
     (
    0.31
    </blockquote>
    0.31
    </i>
    0.30
    ToRefresh
    0.29
    IntoConstraints
    0.29
     instead
    0.29
    Act Density 0.051%

    No Known Activations