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

    Neuronpedia

    INDEX
    Explanations

    quantifiers followed by individuals or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Teacher
    0.73
    Chef
    0.73
    Pastor
    0.71
    Communities
    0.69
     iklan
    0.68
    फॉर्मेशन
    0.66
     biskup
    0.66
     Bürgermeister
    0.66
     Arzt
    0.65
    Engineer
    0.65
    POSITIVE LOGITS
     participants
    2.08
     users
    1.89
     individuals
    1.83
     attendees
    1.69
     occupants
    1.60
     recipients
    1.55
     contributors
    1.54
     applicants
    1.51
     performers
    1.50
    participants
    1.50
    Act Density 0.714%

    No Known Activations