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

    Neuronpedia

    INDEX
    Explanations

    tokens and symbols used in programming or markup languages

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

    measurement values and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.51
     surla
    -0.47
    Rujuakan
    -0.47
    parsedMessage
    -0.42
    enumi
    -0.41
    blockList
    -0.41
     Normdatei
    -0.40
    unhofer
    -0.40
    Географиясе
    -0.40
    VolleyError
    -0.40
    POSITIVE LOGITS
     betweenstory
    0.68
    NameInMap
    0.48
    BufferException
    0.47
    brinco
    0.47
    Personensuche
    0.45
     屋根
    0.45
     resourceCulture
    0.44
    ReusableCell
    0.43
    endregion
    0.42
    Discriminator
    0.41
    Act Density 0.010%

    No Known Activations