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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express totality or inclusiveness

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

    everything or all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.48
     constituents
    -0.40
     tangki
    -0.40
    orcid
    -0.38
    GetEnumerator
    -0.38
    RetentionPolicy
    -0.38
    antía
    -0.37
    なかな
    -0.37
     للمعارف
    -0.36
    UnknownFieldSet
    -0.36
    POSITIVE LOGITS
    everything
    0.96
     everything
    0.92
    Everything
    0.84
     EVERYTHING
    0.83
     Everything
    0.83
    AddTagHelper
    0.65
     הכל
    0.65
     tudo
    0.62
    everywhere
    0.54
    EVERY
    0.54
    Act Density 0.128%

    No Known Activations