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

    Neuronpedia

    INDEX
    Explanations

    living spaces and kitchens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হোট
    0.36
    酒店
    0.34
     nourriture
    0.34
     হোটেল
    0.33
    مرة
    0.32
     możli
    0.32
     incess
    0.32
     préféré
    0.32
    inisc
    0.31
     enregistré
    0.31
    POSITIVE LOGITS
    a
    0.38
     N
    0.35
     n
    0.34
     b
    0.34
    ,
    0.34
    <0xE3>
    0.33
    A
    0.32
     Н
    0.31
     System
    0.31
    System
    0.31
    Act Density 0.001%

    No Known Activations