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

    Neuronpedia

    INDEX
    Explanations

    agile

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    John
    -0.07
    idis
    -0.07
    ature
    -0.07
     diet
    -0.07
    见
    -0.07
     Li
    -0.07
    Only
    -0.07
    Apollo
    -0.07
    лей
    -0.06
     π
    -0.06
    POSITIVE LOGITS
     planners
    0.07
     programmer
    0.07
    _DEFINED
    0.07
    .Deserialize
    0.07
     cooldown
    0.07
     fetisch
    0.06
     канал
    0.06
     newPath
    0.06
     narrowing
    0.06
    <Renderer
    0.06
    Act Density 0.012%

    No Known Activations