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

    Neuronpedia

    INDEX
    Explanations

    spot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AdapterFactory
    -0.07
    .hist
    -0.07
    -widgets
    -0.06
     Cob
    -0.06
     گو
    -0.06
     roast
    -0.06
    rooms
    -0.06
     peace
    -0.06
    eniz
    -0.06
    _STATS
    -0.06
    POSITIVE LOGITS
     Whenever
    0.08
     corrected
    0.07
    ‌توان
    0.07
     Jonah
    0.07
     incorpor
    0.06
     Thompson
    0.06
     continuing
    0.06
     confidentiality
    0.06
     whenever
    0.06
    ?>">
↵
    0.06
    Act Density 0.129%

    No Known Activations