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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .LinearLayout
    -0.07
     cavern
    -0.06
    mousedown
    -0.06
    -ac
    -0.06
    /logo
    -0.06
     arcs
    -0.06
     Elvis
    -0.06
     ®
    -0.06
     prog
    -0.06
     emerge
    -0.06
    POSITIVE LOGITS
    icaret
    0.07
     малыш
    0.07
     upheld
    0.07
    ública
    0.06
     آنها
    0.06
     Israeli
    0.06
     Luckily
    0.06
    '])){↵
    0.06
    ticker
    0.06
     Bruno
    0.06
    Act Density 0.006%

    No Known Activations