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

    Neuronpedia

    INDEX
    Explanations

    university and school names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compras
    0.36
    酒吧
    0.34
    localtime
    0.33
     glorified
    0.32
     town
    0.32
     llegando
    0.32
     použit
    0.32
     forefathers
    0.32
     ristorante
    0.32
     separados
    0.32
    POSITIVE LOGITS
     undergraduate
    0.46
    Faculty
    0.44
    U
    0.43
    University
    0.43
    Graduate
    0.41
     graduate
    0.40
    Associate
    0.40
     Admissions
    0.40
    Mechanical
    0.40
    Donor
    0.40
    Act Density 0.001%

    No Known Activations