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

    Neuronpedia

    INDEX
    Explanations

    expressions of interpersonal interaction and positive social connections

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

    describing people and interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     always
    -0.42
     завжди
    -0.41
     zawsze
    -0.40
     sempre
    -0.40
     siempre
    -0.39
    请联系
    -0.39
     всегда
    -0.38
     fails
    -0.37
     inutile
    -0.37
     همیشه
    -0.36
    POSITIVE LOGITS
    StoryboardSegue
    0.69
    脚注の使い方
    0.66
     seemed
    0.64
     insightful
    0.63
    TagMode
    0.62
    seemed
    0.61
    parsedMessage
    0.61
     intrigued
    0.60
     utafitiHapana
    0.60
     SwitchCompat
    0.60
    Act Density 0.095%

    No Known Activations