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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific structural elements in the text

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

    Follows a sentence-ending punctuation

    np_acts-logits-general · gemini-2.0-flash

    determiner phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    何より
    -0.47
    rrggbb
    -0.46
     nedenle
    -0.38
     yüzden
    -0.38
    めに
    -0.35
    nél
    -0.35
    むしろ
    -0.35
    alam
    -0.34
    endal
    -0.33
     g
    -0.32
    POSITIVE LOGITS
     Theſe
    1.14
    これも
    0.93
    ]--;
    0.92
     Celui
    0.87
     theſe
    0.85
    これは
    0.85
    そちら
    0.84
    これを
    0.84
     iſt
    0.83
     ſche
    0.83
    Act Density 0.693%

    No Known Activations