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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пос
    -0.07
    Fake
    -0.07
    scaling
    -0.06
    .GetAsync
    -0.06
    .card
    -0.06
    ，便
    -0.06
    иболее
    -0.06
     questioning
    -0.06
    _numeric
    -0.06
    并不
    -0.06
    POSITIVE LOGITS
     leggings
    0.07
    不知道
    0.06
    ъек
    0.06
     terme
    0.06
     zvuky
    0.06
     leftovers
    0.06
    -inc
    0.06
    izzly
    0.06
     persona
    0.06
     Levi
    0.06
    Act Density 0.000%

    No Known Activations