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

    Neuronpedia

    INDEX
    Explanations

    technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bà
    -0.07
    onica
    -0.06
     cellular
    -0.06
     nues
    -0.06
     умов
    -0.06
     ü
    -0.06
    variable
    -0.05
     portraits
    -0.05
     qp
    -0.05
     debugger
    -0.05
    POSITIVE LOGITS
     prat
    0.07
     tienes
    0.07
    Cit
    0.07
     teardown
    0.06
    =admin
    0.06
     çözüm
    0.06
     физ
    0.06
    elix
    0.06
    (section
    0.06
    ّة
    0.06
    Act Density 0.000%

    No Known Activations