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

    Neuronpedia

    INDEX
    Explanations

    common pronouns and possessive forms

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

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.72
     NSCoder
    -0.48
     Mahabhar
    -0.46
     TestBed
    -0.46
     Bhag
    -0.43
    __":
    -0.41
     ProtoMessage
    -0.40
    GEBURTSDATUM
    -0.40
    Trayectoria
    -0.39
    AnimationsModule
    -0.39
    POSITIVE LOGITS
     resourceCulture
    0.50
    <bos>
    0.37
    تفصیلات
    0.36
    webElementXpaths
    0.36
    LinkId
    0.35
    apnews
    0.35
    hilangan
    0.35
    ByVersion
    0.35
    0.34
    picks
    0.33
    Act Density 0.025%

    No Known Activations