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

    Neuronpedia

    INDEX
    Explanations

    Code/unstructured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilinx
    -0.06
     pricey
    -0.06
     quoi
    -0.06
    Có
    -0.06
    Elite
    -0.06
     Royale
    -0.06
    BitConverter
    -0.06
     Spacer
    -0.06
     ülk
    -0.06
     yoğun
    -0.06
    POSITIVE LOGITS
     inspections
    0.07
     lad
    0.06
    =".
    0.06
    anvas
    0.06
     želez
    0.06
    egrated
    0.06
     interventions
    0.06
    raz
    0.06
    (default
    0.06
    (amount
    0.06
    Act Density 0.001%

    No Known Activations