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

    Neuronpedia

    INDEX
    Explanations

    Portuguese regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     부정
    0.40
    룬
    0.36
    $?
    0.36
    opter
    0.35
    Feb
    0.34
    ustrated
    0.33
     undetermined
    0.33
    Balances
    0.33
    胺
    0.33
    敗
    0.32
    POSITIVE LOGITS
     CGSize
    0.43
    awing
    0.40
     won
    0.39
     Bailey
    0.39
     st
    0.38
     Kategorie
    0.38
     Sandwich
    0.38
     কালি
    0.37
     Audrey
    0.37
    Basket
    0.37
    Act Density 0.000%

    No Known Activations