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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and annotations in technical documents

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

    after abbreviated names

    np_acts-logits-general · gemini-2.0-flash

    scheduling and retention policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     le
    -0.46
     la
    -0.46
    зин
    -0.44
     Lawrence
    -0.42
     l
    -0.42
    Allocate
    -0.42
     lo
    -0.42
     all
    -0.41
     Lee
    -0.40
     Ben
    -0.39
    POSITIVE LOGITS
     myſelf
    0.90
    ſelf
    0.87
    ⓧ
    0.85
    بوابة
    0.84
     purpoſe
    0.81
    SequentialGroup
    0.81
     BrowserModule
    0.80
    ngdoc
    0.79
     Theſe
    0.79
    oredCriteria
    0.78
    Act Density 0.093%

    No Known Activations