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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job roles or responsibilities in technology and management contexts

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

    Prepositions, conjunctions, or determiners

    np_acts-logits-general · gemini-2.0-flash

    multi-word expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.42
     Jefus
    -0.41
    verhält
    -0.40
     mid
    -0.39
     Efq
    -0.39
     late
    -0.38
    chränk
    -0.37
     Bergamo
    -0.37
     Cagliari
    -0.36
     Chriftian
    -0.36
    POSITIVE LOGITS
     supérieurs
    1.15
     blessés
    1.13
     mères
    1.12
     élevées
    1.11
     stället
    1.10
     varandra
    1.09
     fermés
    1.09
     extérieures
    1.09
     précédents
    1.08
     découvertes
    1.08
    Act Density 1.677%

    No Known Activations