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

    Neuronpedia

    INDEX
    Explanations

    thoughts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     месту
    -0.08
     empir
    -0.08
     restrictions
    -0.08
    inem
    -0.08
     основу
    -0.08
     transmiss
    -0.08
     DCHECK
    -0.07
    etadata
    -0.07
     Voraussetzungen
    -0.07
     stature
    -0.07
    POSITIVE LOGITS
     aloud
    0.09
     humorous
    0.09
    挣
    0.08
    念
    0.08
    -shadow
    0.08
     printed
    0.08
    wish
    0.08
    zijn
    0.08
     Azi
    0.08
    Marcus
    0.08
    Act Density 0.007%

    No Known Activations