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

    Neuronpedia

    INDEX
    Explanations

    business roles and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centers
    0.53
    Centers
    0.53
    division
    0.50
     auditors
    0.50
     divisional
    0.48
     librarians
    0.47
     staffs
    0.47
     offices
    0.46
    utenants
    0.46
     divisions
    0.46
    POSITIVE LOGITS
     CEO
    0.64
     Founder
    0.60
    CEO
    0.56
     ceo
    0.52
     CTO
    0.51
     Founding
    0.48
     Liam
    0.48
     Knock
    0.47
    ceo
    0.46
     Matcha
    0.45
    Act Density 0.013%

    No Known Activations