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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recent events or studies

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

    more recently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.47
    helfen
    -0.47
    ambién
    -0.44
    intios
    -0.43
    InSection
    -0.42
    abetes
    -0.42
     ferons
    -0.40
     defaultstate
    -0.40
    zja
    -0.40
     forcé
    -0.40
    POSITIVE LOGITS
    colgroup
    0.45
    tangentMode
    0.44
    ParallelGroup
    0.41
    цездатний
    0.40
     delivered
    0.40
    readystatechange
    0.40
    RTEX
    0.39
     propOrder
    0.39
    AntiForgeryToken
    0.38
     مشين
    0.37
    Act Density 0.048%

    No Known Activations