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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     상대
    -0.08
     SESSION
    -0.07
     screenings
    -0.06
     streamed
    -0.06
    (dev
    -0.06
     quit
    -0.06
    .plugin
    -0.06
    파
    -0.06
    %d
    -0.06
     Parade
    -0.06
    POSITIVE LOGITS
     anytime
    0.07
     sorumlu
    0.06
     отд
    0.06
    AuthProvider
    0.06
    itles
    0.06
    serialized
    0.06
    .Autowired
    0.06
     대해서
    0.06
     inconvenient
    0.06
     kış
    0.06
    Act Density 0.053%

    No Known Activations