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

    Neuronpedia

    INDEX
    Explanations

    name and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phot
    0.69
    verbs
    0.64
     stoff
    0.63
     plaf
    0.62
    ការ
    0.61
    }}+
    0.60
     rů
    0.60
     пове
    0.60
    شده
    0.60
     ฉ
    0.59
    POSITIVE LOGITS
    暨
    0.76
     Retriever
    0.74
    /-
    0.73
    ره
    0.71
    Fur
    0.70
     mononuclear
    0.70
    फल
    0.70
    ﻕ
    0.69
    ﺏ
    0.68
     निर्धारक
    0.68
    Act Density 0.309%

    No Known Activations