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

    Neuronpedia

    INDEX
    Explanations

    occurrences and variations of the word "false."

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

    `false` followed by negative concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ритори
    -0.38
     ответственности
    -0.30
     Dr
    -0.29
     للمعارف
    -0.29
    Erfolge
    -0.29
    siasi
    -0.28
    向こう
    -0.28
    srcs
    -0.28
    เลย
    -0.28
     Bec
    -0.28
    POSITIVE LOGITS
     False
    0.68
    False
    0.68
     FALSE
    0.62
    ulongan
    0.59
    FALSE
    0.59
    false
    0.56
     miniaturka
    0.55
     AspNetCore
    0.55
     pretense
    0.54
    NullException
    0.54
    Act Density 0.025%

    No Known Activations