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

    Neuronpedia

    INDEX
    Explanations

    pay-per-use pricing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आपका
    0.42
     subscribing
    0.42
     Tut
    0.41
     Donna
    0.41
     bill
    0.41
     Bills
    0.40
     bills
    0.39
     MANAGER
    0.39
     danni
    0.38
     osoba
    0.37
    POSITIVE LOGITS
     pay
    0.55
     Pay
    0.46
    pay
    0.46
    As
    0.43
    Pay
    0.42
     As
    0.40
     canyon
    0.39
    \.
    0.38
    gca
    0.37
    walls
    0.37
    Act Density 0.003%

    No Known Activations