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

    Neuronpedia

    INDEX
    Explanations

    elements related to technical or programming code

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.72
    --)
    -0.70
     الرخصة
    -0.64
    UCKER
    -0.64
    hawar
    -0.64
    sizeCache
    -0.61
     nahilalakip
    -0.61
    BeforeClass
    -0.59
    іга
    -0.59
     NDEBUG
    -0.59
    POSITIVE LOGITS
    expandindo
    0.86
    <eos>
    0.81
    tvguidetime
    0.72
    public
    0.51
     Nebula
    0.50
    ↵↵
    0.49
    hnia
    0.49
     PSM
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.47
    private
    0.47
    Act Density 0.081%

    No Known Activations