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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to data handling and communication in technical contexts

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

    Preceding personal pronouns or nouns

    np_acts-logits-general · gemini-2.0-flash

    for your consideration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MarshalTo
    -0.61
    ütün
    -0.56
    DataContract
    -0.55
    Ђ
    -0.54
    JsonHelper
    -0.54
    basicConfig
    -0.53
    UnusedPrivate
    -0.53
    -0.52
    certs
    -0.52
    protoc
    -0.51
    POSITIVE LOGITS
     ready
    0.77
     to
    0.75
     for
    0.66
    ready
    0.60
     щоб
    0.58
     untuk
    0.57
     Ready
    0.57
     для
    0.56
    以便
    0.56
    供
    0.55
    Act Density 0.445%

    No Known Activations