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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _COUNTER
    -0.07
    kj
    -0.06
    orghini
    -0.06
     cc
    -0.06
    [user
    -0.06
    k
    -0.06
     incompetence
    -0.06
     vững
    -0.06
     pastoral
    -0.06
    .PNG
    -0.06
    POSITIVE LOGITS
    σταν
    0.06
     여러
    0.06
     registering
    0.06
     іншими
    0.06
     одну
    0.06
    лаж
    0.06
    ằm
    0.06
    978
    0.06
    alytics
    0.06
    .Tele
    0.06
    Act Density 0.020%

    No Known Activations