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

    Neuronpedia

    INDEX
    Explanations

    references to methods, proposals, and advancements in technology

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

    technische Spezifitäten

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.57
    RuleContext
    -0.47
    المناصب
    -0.44
    banden
    -0.40
    awtextra
    -0.39
    exao
    -0.38
     runs
    -0.38
    oneofs
    -0.37
    Diweddarwch
    -0.37
    Runs
    -0.36
    POSITIVE LOGITS
    Erstellt
    0.43
     desglose
    0.43
    YSQL
    0.43
    ⤹
    0.41
    Portale
    0.40
    她們
    0.40
     depolar
    0.40
     dyno
    0.39
     fiss
    0.38
    ruit
    0.37
    Act Density 0.062%

    No Known Activations