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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dialogue-related phrases

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

    Quoted speech, followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    dialogue punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    forName
    -0.66
     Efq
    -0.65
     Anſ
    -0.64
     δὲ
    -0.64
     fubject
    -0.64
     useAuth
    -0.63
     raiſ
    -0.63
     AppColors
    -0.62
    Kesimpulan
    -0.62
     parkir
    -0.60
    POSITIVE LOGITS
     he
    0.68
    MessageTagHelper
    0.62
    MigrationBuilder
    0.61
    :])
    0.59
    ]));
    0.59
    ↵↵
    0.58
    ]));
    0.57
    )}</
    0.56
    ')")
    0.56
    ']);
    0.56
    Act Density 0.028%

    No Known Activations