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

    Neuronpedia

    INDEX
    Explanations

    equality and comparison operators in code

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

    "==" or similar repeated sequences

    np_acts-logits-general · gemini-2.0-flash

    replace text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.70
     kasarigan
    -0.55
     OnTrigger
    -0.50
    inburgh
    -0.50
     FH
    -0.50
     говоря
    -0.49
    These
    -0.49
    あり
    -0.48
     Эти
    -0.48
     knex
    -0.47
    POSITIVE LOGITS
    ")==
    1.01
    ']==
    0.86
     ==
    0.86
    ================
    0.81
    withstanding
    0.79
     null
    0.77
    rzost
    0.77
    TRIBUTES
    0.77
    )==
    0.77
    τικ
    0.76
    Act Density 0.081%

    No Known Activations