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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their actions or relationships

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

    Follows a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    pronouns and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.58
    KommentareTeilen
    -0.55
    BeginInit
    -0.43
    cation
    -0.41
    bootstrapcdn
    -0.40
     rhestr
    -0.39
    なり
    -0.39
    kiwa
    -0.37
     FontFamily
    -0.37
    tés
    -0.37
    POSITIVE LOGITS
    жидан
    0.49
    ModelAdmin
    0.45
     okuyayım
    0.40
    ItemBackground
    0.40
     próprios
    0.40
    zarchiwizowane
    0.39
    ężczy
    0.39
    ztyn
    0.38
     насељу
    0.38
     فريبيس
    0.37
    Act Density 0.613%

    No Known Activations