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

    Neuronpedia

    INDEX
    Explanations

    dialogue expressions and interactions in conversation

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

    Informal conversational responses

    np_acts-logits-general · gemini-2.0-flash

    conversational interjections and reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.82
     >=",
    -0.81
    OGND
    -0.77
     Paglinawan
    -0.77
    GEBURTSDATUM
    -0.74
     Normdatei
    -0.69
    PMailer
    -0.67
     '\\;'
    -0.67
     متعلقه
    -0.66
     виправивши
    -0.65
    POSITIVE LOGITS
    …
    0.66
     fossa
    0.55
    ...
    0.54
    ….
    0.52
    ..
    0.51
    ....
    0.47
     approu
    0.47
    anskje
    0.47
     kiệm
    0.46
    principalColumn
    0.45
    Act Density 0.090%

    No Known Activations