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

    Neuronpedia

    INDEX
    Explanations

    Gatsby/Phantom of the Opera

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unit
    -0.08
     Cortex
    -0.08
     виде
    -0.08
     Sche
    -0.08
    .adapters
    -0.08
     Target
    -0.08
     Leakage
    -0.07
     Gauge
    -0.07
     дел
    -0.07
     polvo
    -0.07
    POSITIVE LOGITS
    peak
    0.08
     曲
    0.08
     generosity
    0.08
     apresentações
    0.08
     وڏي
    0.08
     Kail
    0.08
     modifies
    0.08
     eigenlijk
    0.08
     وڏ
    0.08
    ong
    0.08
    Act Density 0.003%

    No Known Activations