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

    Neuronpedia

    INDEX
    Explanations

    GABA and specific acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bhavati
    0.47
     atrocities
    0.47
     ebenfalls
    0.46
     betrayal
    0.46
     jaaye
    0.46
     dupatta
    0.44
    ungkap
    0.42
    ઈ
    0.42
    覚
    0.42
    assam
    0.41
    POSITIVE LOGITS
    Wiki
    0.49
    Graph
    0.48
     principles
    0.45
    架构
    0.45
     tecnologie
    0.45
    Build
    0.44
     standards
    0.44
    通用
    0.43
    Process
    0.43
    镛
    0.43
    Act Density 0.003%

    No Known Activations