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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     안
    -0.07
    합
    -0.07
     edilmiş
    -0.06
    Ingredients
    -0.06
     coron
    -0.06
     glaciers
    -0.06
     Advisory
    -0.06
    uggested
    -0.06
    -caption
    -0.06
     chill
    -0.06
    POSITIVE LOGITS
    _tracker
    0.06
     Mama
    0.06
    baby
    0.06
    BarItem
    0.06
    _semaphore
    0.06
    adors
    0.06
     taxes
    0.06
     INF
    0.06
    hma
    0.06
     wre
    0.06
    Act Density 0.066%

    No Known Activations