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

    Neuronpedia

    INDEX
    Explanations

    phrases and words in Arabic and Japanese contexts, indicating preferences or choices

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

    Non-English currency symbols and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    currency and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.62
    Jeografia
    -0.60
     تضيفلها
    -0.57
    الدراسه
    -0.53
    Autoritní
    -0.52
     ſta
    -0.52
     houſe
    -0.49
    neſs
    -0.48
     obſ
    -0.48
     ligiloj
    -0.47
    POSITIVE LOGITS
     Segurança
    0.43
     politiet
    0.40
     miljø
    0.39
     Ensino
    0.38
     tenisky
    0.37
     atmósfera
    0.36
    杓
    0.36
     žaid
    0.36
     Trabalho
    0.36
     pescoço
    0.36
    Act Density 0.016%

    No Known Activations