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

    Neuronpedia

    INDEX
    Explanations

    Older adults

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undeniable
    -0.08
     tł
    -0.08
     TBD
    -0.08
     ختم
    -0.07
     Inde
    -0.07
     തീ
    -0.07
     quinta
    -0.07
     bih
    -0.07
     jel
    -0.07
     guh
    -0.07
    POSITIVE LOGITS
     cognit
    0.10
     отличается
    0.09
     respondents
    0.09
    urvey
    0.08
     отличаются
    0.08
     periods
    0.08
     peers
    0.08
     aides
    0.08
     зачем
    0.08
    PEc
    0.08
    Act Density 0.013%

    No Known Activations