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

    Neuronpedia

    INDEX
    Explanations

    signal status and message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    शंकर
    0.61
     manicure
    0.58
     quirks
    0.58
     sixties
    0.57
     വരുന്ന
    0.57
     railings
    0.55
     moistur
    0.55
     σχε
    0.55
     পরবর্তীতে
    0.55
     preposition
    0.55
    POSITIVE LOGITS
    8
    0.68
    ော့
    0.67
    德
    0.67
    는
    0.66
    5
    0.65
    ди
    0.64
    3
    0.64
    人
    0.64
    are
    0.63
     Bên
    0.63
    Act Density 0.091%

    No Known Activations