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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation, particularly involving parentheses and certain symbols

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

    Mathematical expressions starting with parentheses

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </thead>
    -0.50
     TextStyle
    -0.49
    endpush
    -0.48
    agoza
    -0.46
    uci
    -0.45
    голо
    -0.44
    annten
    -0.44
    язы
    -0.44
    дні
    -0.43
    ips
    -0.42
    POSITIVE LOGITS
     initComponents
    0.80
    }}(\
    0.71
     ویکی‌پدیای
    0.70
    ModelSerializer
    0.66
     виправивши
    0.64
     Jurí
    0.62
     varandra
    0.62
    aculture
    0.62
     stället
    0.61
     }}(\
    0.61
    Act Density 0.420%

    No Known Activations