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

    Neuronpedia

    INDEX
    Explanations

    complex narrative structures and character development in storytelling

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

    unawareness or surprise

    np_acts-logits-general · gemini-2.0-flash

    unexpected or unaware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.51
    ?>
    -0.51
    viewDidLoad
    -0.50
    yticks
    -0.49
    FactoryBean
    -0.48
    }-${
    -0.48
    SizeMode
    -0.48
    zelt
    -0.48
    NgModule
    -0.47
    RectF
    -0.47
    POSITIVE LOGITS
     unaware
    0.88
    沒想到
    0.86
    まさか
    0.85
    没想到
    0.84
     unsus
    0.78
    little
    0.72
     little
    0.70
     Unbe
    0.68
    想不到
    0.66
     unknowingly
    0.65
    Act Density 0.185%

    No Known Activations