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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate explanations or descriptions

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

    という (naming/quoting)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.51
    ScopeManager
    -0.45
     صوتيه
    -0.43
    cerv
    -0.42
     '@/
    -0.42
    genta
    -0.40
    }{*}{
    -0.39
    scen
    -0.39
    bora
    -0.39
    patron
    -0.38
    POSITIVE LOGITS
    という
    0.68
    라는
    0.63
    pecabe
    0.59
    するという
    0.59
     notícia
    0.54
     considérons
    0.54
     notizia
    0.52
     idéia
    0.51
     tatuagem
    0.50
     tremendous
    0.50
    Act Density 0.009%

    No Known Activations