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

    Neuronpedia

    INDEX
    Explanations

    high-frequency numerical values or identifiers

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

    code and configuration structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.59
    SequentialGroup
    -0.58
    yntaxException
    -0.56
    хьтан
    -0.56
    SupportActionBar
    -0.54
    بوابة
    -0.52
     Савезне
    -0.51
    ParallelGroup
    -0.51
     autorytatywna
    -0.51
    ImageContext
    -0.50
    POSITIVE LOGITS
     gebou
    0.43
    ец
    0.43
    middels
    0.39
    youts
    0.37
     mengel
    0.37
    redient
    0.36
    Commonwealth
    0.36
     dingen
    0.36
     Buildings
    0.35
    USSR
    0.35
    Act Density 0.002%

    No Known Activations