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

    Neuronpedia

    INDEX
    Explanations

    API usage and specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ne
    0.93
    n
    0.83
    (
    0.83
    й
    0.82
    ]
    0.81
    y
    0.81
    set
    0.75
    va
    0.72
    ment
    0.71
    nse
    0.71
    POSITIVE LOGITS
     luciferase
    0.94
     anastom
    0.88
     Neend
    0.80
    ляется
    0.79
     phytochemical
    0.78
     Cádiz
    0.78
     координаты
    0.78
     реаль
    0.78
     смы
    0.78
     peroxidase
    0.78
    Act Density 0.187%

    No Known Activations