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

    Neuronpedia

    INDEX
    Explanations

    terms related to judgment and evaluations

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

    ending in "-ly", "-al", "-able", "-ment", or "-ous"

    np_acts-logits-general · gemini-2.0-flash

    judgment, health, advantage, avoid, advent, account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portale
    -0.50
    حياتها
    -0.42
    United
    -0.40
     duros
    -0.38
     gibi
    -0.37
    بوابة
    -0.36
    Others
    -0.36
     welchem
    -0.36
    женный
    -0.36
     halben
    -0.36
    POSITIVE LOGITS
    BibitemShut
    0.80
    httphttps
    0.63
     Shakspeare
    0.61
    delivr
    0.60
     theore
    0.59
     beaute
    0.59
    ſelf
    0.58
    ztály
    0.57
    thme
    0.56
    vellous
    0.56
    Act Density 0.461%

    No Known Activations