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

    Neuronpedia

    INDEX
    Explanations

    developed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fluffy
    -0.07
     matchmaking
    -0.06
     subtitles
    -0.06
     arşiv
    -0.06
    Segments
    -0.06
     stadium
    -0.06
     HDD
    -0.06
     playground
    -0.06
    YTE
    -0.06
    (sock
    -0.06
    POSITIVE LOGITS
     Stainless
    0.07
    -related
    0.07
    packages
    0.06
    acious
    0.06
    진
    0.06
     races
    0.06
    prav
    0.06
    olian
    0.06
    prs
    0.06
     omn
    0.06
    Act Density 0.045%

    No Known Activations