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

    Neuronpedia

    INDEX
    Explanations

    personnel and job titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ionage
    0.35
     lawsuits
    0.34
    Actor
    0.32
    各项
    0.32
    写法
    0.31
    旅客
    0.31
    論文
    0.31
     flourishing
    0.30
    jekte
    0.30
    実績
    0.30
    POSITIVE LOGITS
     technicians
    0.95
     technician
    0.92
     engineers
    0.80
     librarians
    0.80
     administrators
    0.79
     librarian
    0.78
    工程师
    0.78
     administrator
    0.77
     coordinators
    0.77
     nurses
    0.77
    Act Density 0.077%

    No Known Activations