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

    Neuronpedia

    INDEX
    Explanations

    academic course codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dun
    0.40
    Dun
    0.38
    ittäin
    0.37
     Rape
    0.36
    magic
    0.35
     Bol
    0.35
    λύ
    0.35
     dun
    0.35
     Roku
    0.35
     Voz
    0.35
    POSITIVE LOGITS
     ECON
    0.63
     ENG
    0.59
    ET
    0.59
     EDUC
    0.57
     PHYS
    0.55
     ENV
    0.54
    MGMT
    0.52
    PSY
    0.52
     EN
    0.51
    EDUC
    0.50
    Act Density 0.003%

    No Known Activations