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

    Neuronpedia

    INDEX
    Explanations

    guidelines and Cats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    दर्भ
    0.37
     दुष्प्रभाव
    0.37
     unve
    0.36
     classi
    0.36
    eking
    0.35
     CDF
    0.35
     सहज
    0.35
    usin
    0.34
     Cagliari
    0.34
    planet
    0.34
    POSITIVE LOGITS
     Cats
    0.85
    Cats
    0.83
     Poc
    0.76
     cats
    0.64
    cats
    0.61
     Sullivan
    0.58
    POC
    0.55
     poc
    0.54
    poc
    0.54
     POC
    0.54
    Act Density 0.003%

    No Known Activations