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

    Neuronpedia

    INDEX
    Explanations

    meta and its derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.56
    in
    0.54
    inte
    0.52
    ine
    0.51
    𝙣
    0.51
    ماء
    0.51
     رائ
    0.51
    Spl
    0.50
    ၂
    0.49
    م
    0.48
    POSITIVE LOGITS
     meta
    1.02
     Meta
    0.91
    メタ
    0.89
     MET
    0.88
     META
    0.88
     мета
    0.86
     metas
    0.85
     mét
    0.85
     Metadata
    0.84
    MET
    0.80
    Act Density 0.110%

    No Known Activations