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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terms and expressions related to methodologies and protocols

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

    procedural context nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emploi
    -0.46
     pinulongan
    -0.46
    "},
    -0.44
     المعيارى
    -0.44
    Хьажоргаш
    -0.43
     raiſ
    -0.43
    "):
    -0.41
    "),
    -0.41
    '),
    -0.41
     tapaht
    -0.41
    POSITIVE LOGITS
    alis
    0.46
     scatola
    0.45
    RTEX
    0.43
    .
    0.42
    alyse
    0.41
    allowing
    0.40
    SPF
    0.40
     enjoys
    0.40
    <eos>
    0.40
    jects
    0.40
    Act Density 0.091%

    No Known Activations