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

    Neuronpedia

    INDEX
    Explanations

    words often found in software development documentation, especially related to source control, versioning, team work, and project management

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UpInside
    -0.63
    UrlResolution
    -0.62
    tened
    -0.55
    ädie
    -0.52
     GenerationType
    -0.52
    Custo
    -0.52
    TargetException
    -0.51
    Stal
    -0.51
    toral
    -0.50
     Custo
    -0.50
    POSITIVE LOGITS
     project
    1.19
    project
    1.09
     projects
    1.09
    Project
    1.06
     Project
    1.05
     proyek
    1.04
    PROJECT
    1.02
     PROJECT
    0.99
     Projects
    0.97
    Projects
    0.96
    Act Density 1.542%

    No Known Activations