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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance

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

    superlative or primary indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.55
    хьтан
    -0.52
    HtmlAttribute
    -0.49
    󠁴
    -0.48
    BeginInit
    -0.48
    jago
    -0.46
    ChildIndex
    -0.46
    hyrchwyd
    -0.45
    stdlib
    -0.44
     inoxydable
    -0.43
    POSITIVE LOGITS
    țiunea
    0.37
     dilemma
    0.36
     الاطلاع
    0.36
    HasAnnotation
    0.36
     approach
    0.35
    chließ
    0.35
     is
    0.34
     volgen
    0.34
     خدمت
    0.34
     цель
    0.33
    Act Density 0.050%

    No Known Activations