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

    Neuronpedia

    INDEX
    Explanations

    data and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     considered
    0.40
    Especially
    0.39
    탈
    0.39
     realized
    0.39
     Herald
    0.39
     bức
    0.39
    ಯು
    0.38
    Ethoxy
    0.38
    considered
    0.38
     especially
    0.38
    POSITIVE LOGITS
     vaginale
    0.45
     alfalfa
    0.45
    </h3>
    0.45
     embol
    0.44
     яй
    0.44
     Merlot
    0.44
     btn
    0.43
     afecta
    0.43
     sputum
    0.43
     عندما
    0.43
    Act Density 0.001%

    No Known Activations