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

    Neuronpedia

    INDEX
    Explanations

    px;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⓐ
    0.40
     yol
    0.39
    苏
    0.38
     observability
    0.38
    乓
    0.38
    Fighting
    0.38
     plasticity
    0.37
     treball
    0.37
     quan
    0.37
     maneuvering
    0.37
    POSITIVE LOGITS
     doesn
    0.45
    locale
    0.42
    yscraper
    0.40
    ocultural
    0.40
    ไม่
    0.40
     Monographs
    0.38
     விமர்
    0.37
    figsize
    0.37
    unittest
    0.37
     deprecated
    0.37
    Act Density 0.001%

    No Known Activations