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

    Neuronpedia

    INDEX
    Explanations

    various identifiers and metadata often associated with programming or technical documentation

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

    user identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eniably
    -0.37
    protoimpl
    -0.37
    matchCondition
    -0.36
     ACCORD
    -0.34
     tæn
    -0.34
    testens
    -0.34
    的吗
    -0.33
    -0.33
     Auft
    -0.33
    corazón
    -0.32
    POSITIVE LOGITS
    expandindo
    0.71
     referenties
    0.63
    Diweddarwch
    0.62
    KommentareTeilen
    0.57
    CBN
    0.54
     ſind
    0.54
     uska
    0.54
    }{*}{}
    0.54
    ſelves
    0.54
     ExecuteAsync
    0.54
    Act Density 0.017%

    No Known Activations