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

    Neuronpedia

    INDEX
    Explanations

    assignment operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mixtures
    0.86
    cohols
    0.83
    Temperature
    0.77
     walled
    0.74
    Temperatura
    0.72
    मोरी
    0.69
     Liquids
    0.69
     Temperature
    0.68
    性和
    0.68
    нинград
    0.68
    POSITIVE LOGITS
     =
    1.23
     ==
    0.97
     !=
    0.97
    =$(
    0.95
     হিসেবে
    0.93
    ="";
    0.89
    !=
    0.87
    ＝
    0.87
    =
    0.87
     $=
    0.86
    Act Density 0.011%

    No Known Activations