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

    Neuronpedia

    INDEX
    Explanations

    SQL group by clause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aide
    -0.09
     ць
    -0.08
    FONT
    -0.08
     има
    -0.08
     disp
    -0.08
     الجر
    -0.08
     aeg
    -0.08
     spreken
    -0.08
     atelier
    -0.08
    טער
    -0.08
    POSITIVE LOGITS
     Besides
    0.09
     Qué
    0.09
     Along
    0.09
    Along
    0.08
     correlated
    0.08
     Non
    0.08
     Serializable
    0.08
    出
    0.08
    Besides
    0.07
     Appe
    0.07
    Act Density 0.004%

    No Known Activations