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

    Neuronpedia

    INDEX
    Explanations

    strong adjectives and descriptors related to presentations or reports

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

    descriptive adjectives before nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikispecies
    -0.32
    Résumé
    -0.31
    ウター
    -0.31
    eniendo
    -0.31
     cikk
    -0.30
    Atsauces
    -0.30
    ンピオン
    -0.29
     referenties
    -0.29
    BagConstraints
    -0.29
     pagkak
    -0.29
    POSITIVE LOGITS
    hens
    0.49
     onResponse
    0.49
    umel
    0.49
     Teflon
    0.48
     ब्रेकडाउन
    0.48
    nestjs
    0.48
     rejo
    0.48
    chitis
    0.47
    ruitment
    0.47
     Haze
    0.47
    Act Density 0.228%

    No Known Activations