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

    Neuronpedia

    INDEX
    Explanations

    conditional outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    њ
    0.49
    trifluoromethyl
    0.47
    ри
    0.47
    မှု
    0.47
    ни
    0.45
     reunião
    0.45
     торговли
    0.44
    日々
    0.43
    drinking
    0.43
     vírus
    0.43
    POSITIVE LOGITS
    τερ
    0.46
    usele
    0.43
    inoa
    0.43
     adjunction
    0.41
    em
    0.39
     enhancer
    0.39
     বাড়ির
    0.39
     valeur
    0.38
    onta
    0.38
     پاس
    0.38
    Act Density 0.001%

    No Known Activations