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

    Neuronpedia

    INDEX
    Explanations

    questions and conversational fragments

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

    Follows "of", comma, or question words

    np_acts-logits-general · gemini-2.0-flash

    demonstrative pronouns / "those"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.96
    CreateModel
    -0.75
    Personensuche
    -0.69
    saraba
    -0.69
     AssemblyCulture
    -0.68
     lenker
    -0.68
    TintMode
    -0.65
    ()]);
    -0.65
    Indeed
    -0.65
     EconPapers
    -0.63
    POSITIVE LOGITS
    那种
    1.05
     those
    1.02
     aquela
    0.97
     aquele
    0.91
    那種
    0.91
    those
    0.90
     Those
    0.83
    那个
    0.82
    やつ
    0.80
     THOSE
    0.79
    Act Density 0.242%

    No Known Activations