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

    Neuronpedia

    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    保险
    -0.07
     registration
    -0.06
    -course
    -0.06
     Brave
    -0.06
    　　　　　　　　　　　　
    -0.06
    Registr
    -0.06
    Compra
    -0.06
     boyfriend
    -0.06
     authors
    -0.06
     expedition
    -0.06
    POSITIVE LOGITS
    ्डल
    0.07
     terminating
    0.07
     tuz
    0.06
     dov
    0.06
    etically
    0.06
     giác
    0.06
    [item
    0.06
     способ
    0.06
     topp
    0.06
    -lock
    0.06
    Act Density 0.123%

    No Known Activations