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

    Neuronpedia

    INDEX
    Explanations

    model/viewmodel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dzi
    -0.07
    #ae
    -0.06
     욕
    -0.06
     Martin
    -0.06
    \">↵
    -0.06
     niece
    -0.06
     footsteps
    -0.06
    Den
    -0.06
    <select
    -0.06
     step
    -0.06
    POSITIVE LOGITS
     ViewModel
    0.06
     incon
    0.06
     awaiting
    0.06
    IRQ
    0.06
     praw
    0.06
    acts
    0.06
     Stones
    0.06
    OUGH
    0.06
     DeV
    0.06
     CDDL
    0.06
    Act Density 0.018%

    No Known Activations