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

    Neuronpedia

    INDEX
    Explanations

    meta and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.57
    ل
    0.54
    ون
    0.51
    ine
    0.48
    inama
    0.48
    𝙣
    0.48
    ater
    0.47
    ህ
    0.47
    inte
    0.47
    inning
    0.47
    POSITIVE LOGITS
     meta
    1.02
     мета
    0.95
     Metadata
    0.92
     Meta
    0.92
    メタ
    0.92
     META
    0.88
     mét
    0.84
    MET
    0.84
     metas
    0.84
     MET
    0.82
    Act Density 0.131%

    No Known Activations