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

    Neuronpedia

    INDEX
    Explanations

    elements related to styling and formatting in code

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

    lemma references like Lem:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.60
    KURZBESCHREIBUNG
    -0.55
     defaultstate
    -0.54
    istoitu
    -0.53
     ویکی‌پدی
    -0.53
    </thead>
    -0.50
    ThroughAttribute
    -0.50
     snippetHide
    -0.49
    ंदीखरीदारी
    -0.49
     FileInputStream
    -0.48
    POSITIVE LOGITS
    aliyun
    0.45
    assured
    0.44
    Assured
    0.40
    UnitTesting
    0.40
    lunda
    0.39
    outSlope
    0.39
    assertNotNull
    0.38
    anteed
    0.37
     orejas
    0.36
    yarnpkg
    0.35
    Act Density 0.000%

    No Known Activations