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

    Neuronpedia

    INDEX
    Explanations

    names and their continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sidebar
    0.25
     Mermaid
    0.25
     quirky
    0.25
     girly
    0.25
     Hogwarts
    0.24
    柔软
    0.24
    উদাহরণ
    0.24
     sassy
    0.24
     Chameleon
    0.24
     Humming
    0.24
    POSITIVE LOGITS
    l
    0.29
    ot
    0.26
    ko
    0.26
    ers
    0.25
    ys
    0.25
    v
    0.25
    z
    0.25
    j
    0.25
    re
    0.25
    IO
    0.24
    Act Density 0.008%

    No Known Activations