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

    Neuronpedia

    INDEX
    Explanations

    polite greetings and formal salutations

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

    Text after salutations or closings

    np_acts-logits-general · gemini-2.0-flash

    separators or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ruptedException
    -0.81
     ?>>
    -0.78
    %");
    -0.74
    )";
    -0.72
    $")
    -0.71
    ?");
    -0.71
    urlpatterns
    -0.71
     @"/
    -0.70
    gheny
    -0.70
    Parcelize
    -0.70
    POSITIVE LOGITS
    ↵↵
    0.63
    :
    0.60
    Personendaten
    0.57
    All
    0.56
    ↵
    0.51
     All
    0.49
    Well
    0.49
     Unfortunately
    0.48
    Unfortunately
    0.46
     Well
    0.43
    Act Density 0.076%

    No Known Activations