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

    Neuronpedia

    INDEX
    Explanations

    reflection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rgb
    -0.08
     organizer
    -0.08
    Organizer
    -0.08
    ्यान
    -0.08
     Recon
    -0.07
     reú
    -0.07
     recon
    -0.07
     woo
    -0.07
    سط
    -0.07
     dedica
    -0.07
    POSITIVE LOGITS
     зл
    0.08
     सीमा
    0.08
    违规
    0.08
     незакон
    0.07
     violated
    0.07
     violating
    0.07
    Boundary
    0.07
     undesirable
    0.07
     schicken
    0.07
    boundary
    0.07
    Act Density 0.003%

    No Known Activations