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

    Neuronpedia

    INDEX
    Explanations

    comparison and list operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    দুর
    0.39
    牖
    0.39
    黑暗
    0.38
    embry
    0.38
     হাসি
    0.38
     Spal
    0.38
     Chiesa
    0.38
     ተግባ
    0.38
     glandular
    0.37
    繊
    0.37
    POSITIVE LOGITS
     Inequality
    0.71
     inequality
    0.70
     ग्रेटर
    0.70
     !=
    0.68
    neq
    0.65
     Greater
    0.63
     equals
    0.63
    等于
    0.63
     !==
    0.61
     unequal
    0.61
    Act Density 0.030%

    No Known Activations