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

    Neuronpedia

    INDEX
    Explanations

    references to themes and theme-related terminology

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

    "theme" or "themes"

    np_acts-logits-general · gemini-2.0-flash

    theme and topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     titulaire
    -0.57
     elettron
    -0.55
     blancs
    -0.54
     Tobin
    -0.53
     citoy
    -0.50
    isy
    -0.50
     singuli
    -0.49
     voetballer
    -0.49
    roves
    -0.48
    qtd
    -0.48
    POSITIVE LOGITS
     themes
    1.24
    themes
    1.15
     Theme
    1.12
     theme
    1.10
    THEME
    1.08
     Themes
    1.04
    Themes
    1.04
    theme
    1.04
    Theme
    0.98
     THEME
    0.96
    Act Density 0.061%

    No Known Activations