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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methods and principles in research contexts

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

    critical, strong, low, diffusion, thermo, additive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    something
    -0.40
    Välislingid
    -0.40
     enfans
    -0.36
    XmlRootElement
    -0.35
    Personensuche
    -0.34
    发表于
    -0.34
     Roskov
    -0.34
    ])){
    -0.33
     հղումներ
    -0.32
     SOMETHING
    -0.32
    POSITIVE LOGITS
     ſondern
    0.56
    <unused51>
    0.56
    <unused47>
    0.56
    [@BOS@]
    0.55
    <unused80>
    0.55
    <unused28>
    0.55
    <unused74>
    0.55
    <unused42>
    0.55
    <unused14>
    0.55
    <unused23>
    0.55
    Act Density 0.174%

    No Known Activations