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

    Neuronpedia

    INDEX
    Explanations

    believe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thiếu
    -0.07
    kest
    -0.06
    -card
    -0.06
     tích
    -0.06
    Ticket
    -0.06
     Specific
    -0.06
     loyalty
    -0.06
    elop
    -0.06
     بول
    -0.06
    press
    -0.06
    POSITIVE LOGITS
     kita
    0.07
     когда
    0.06
     tohoto
    0.06
     davon
    0.06
     pls
    0.06
    ича
    0.06
     奥
    0.06
     Rapids
    0.06
    976
    0.06
     Spart
    0.06
    Act Density 0.001%

    No Known Activations