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

    Neuronpedia

    INDEX
    Explanations

    card or cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reonine
    0.82
     Sonn
    0.76
     बोस
    0.69
     வயி
    0.66
    Chal
    0.65
     Locks
    0.65
    碓
    0.65
     Kochubei
    0.64
     बुन्देल
    0.64
    Saxon
    0.63
    POSITIVE LOGITS
     cards
    4.79
     card
    4.77
     Cards
    4.36
    Card
    4.34
    cards
    4.27
     Card
    4.27
    Cards
    4.22
    card
    4.15
    カード
    3.87
     कार्ड
    3.83
    Act Density 0.350%

    No Known Activations