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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IndentedString
    -0.65
     kasarigan
    -0.62
    IsInitialized
    -0.57
    had
    -0.51
    Cyfeiriadau
    -0.49
    dos
    -0.49
    солю
    -0.49
    Pati
    -0.49
    mota
    -0.48
    ništ
    -0.48
    POSITIVE LOGITS
    SBATCH
    0.59
    tvguidetime
    0.59
    Transkript
    0.56
    scientific
    0.53
     scientific
    0.52
    Луч
    0.52
    SpringBootTest
    0.52
     viewDidLoad
    0.52
    #
    0.52
    gonic
    0.51
    Act Density 0.001%

    No Known Activations