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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    conversational interjections or greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.76
    RenderAtEndOf
    -0.64
    -0.63
    __':

    -0.62
     DbType
    -0.61
    "),

    -0.61
    __":

    -0.60
    (),

    -0.60
    ),

    -0.59
    ],

    -0.59
    POSITIVE LOGITS
    BTW
    0.60
    ちなみに
    0.58
    <eos>
    0.58
     oublié
    0.58
    tablissements
    0.57
    Grüße
    0.55
    Открыть
    0.55
     btw
    0.54
    顺便
    0.54
     Paging
    0.53
    Act Density 0.305%
    No Known Activations