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

    Neuronpedia

    INDEX
    Explanations

    code structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    閉
    -0.08
     Beverage
    -0.06
    -security
    -0.06
     Radi
    -0.06
    .animate
    -0.06
    dens
    -0.06
     callers
    -0.06
    (tab
    -0.06
    <\/
    -0.06
    .Clock
    -0.06
    POSITIVE LOGITS
    μβ
    0.07
     incorrectly
    0.07
     township
    0.07
     unw
    0.06
    .Contracts
    0.06
     Salman
    0.06
    ('{
    0.06
    Mine
    0.06
    (&___
    0.06
     WANT
    0.06
    Act Density 0.018%

    No Known Activations