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

    Neuronpedia

    INDEX
    Explanations

    titles and roles associated with leadership and management positions

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

    director and related leadership roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WaitGroup
    -0.38
     breath
    -0.36
     freaking
    -0.35
    salud
    -0.35
     experimentation
    -0.35
     embuti
    -0.34
     ADULT
    -0.34
     pasaj
    -0.34
     stone
    -0.34
     débar
    -0.34
    POSITIVE LOGITS
     director
    0.98
     Director
    0.96
    director
    0.93
     directors
    0.89
    Director
    0.86
     directeur
    0.85
     Directors
    0.85
     direttore
    0.85
     directrice
    0.84
    Directeur
    0.82
    Act Density 0.006%

    No Known Activations