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

    Neuronpedia

    INDEX
    Explanations

    words associated with events and locations within a narrative

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    новништво
    -0.59
     géographique
    -0.59
    setArguments
    -0.54
    anging
    -0.49
     المعيارى
    -0.49
     betweenstory
    -0.48
    pon
    -0.48
    ########.
    -0.46
     stratégies
    -0.46
    ʃ
    -0.46
    POSITIVE LOGITS
    Rüyada
    0.63
     leased
    0.61
    CppMethod
    0.59
     occupied
    0.58
     dyna
    0.56
     skimmed
    0.54
    Scénario
    0.52
     uska
    0.52
    ">'.$
    0.52
     noqa
    0.51
    Act Density 1.576%

    No Known Activations