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

    Neuronpedia

    INDEX
    Explanations

    function descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mettant
    0.78
     లో
    0.75
    держи
    0.74
     ट्रायंगल
    0.70
    *****",
    0.70
    કના
    0.70
    ();//
    0.69
    ////////
    0.69
    ayatiti
    0.69
    सदीय
    0.69
    POSITIVE LOGITS
    know
    0.55
     know
    0.52
    ground
    0.48
    oc
    0.48
     asteroid
    0.48
    ↵
    0.48
    utra
    0.47
     Latin
    0.47
     Know
    0.47
    ন
    0.46
    Act Density 0.031%

    No Known Activations