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

    Neuronpedia

    INDEX
    Explanations

    code, especially Java or C# code with cross-platform elements, including UI and cloud services

    oai_token-act-pair · gemini-2.0-flash

    Code, schedules, policies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summer
    -0.76
     briefing
    -0.76
     evening
    -0.75
     quick
    -0.74
     tutorial
    -0.73
    overview
    -0.73
     overview
    -0.73
     welcome
    -0.73
     tour
    -0.71
     basics
    -0.70
    POSITIVE LOGITS
     cells
    0.55
     prote
    0.55
     animal
    0.53
    essoas
    0.52
     depositors
    0.51
     entities
    0.51
     mã
    0.50
     animals
    0.50
     electrons
    0.49
     persons
    0.49
    Act Density 9.686%

    No Known Activations