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

    Neuronpedia

    INDEX
    Explanations

    SQL databases and transactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    роме
    -0.07
     як
    -0.07
    Hall
    -0.07
    .yang
    -0.06
    共和国
    -0.06
    .Restrict
    -0.06
    .guard
    -0.06
    .Queue
    -0.06
     editar
    -0.06
     편집
    -0.06
    POSITIVE LOGITS
    ينه
    0.07
    cka
    0.07
    itating
    0.06
    121
    0.06
     writ
    0.06
     Oswald
    0.06
    ooky
    0.06
     Blonde
    0.06
    _generated
    0.06
    {}{↵
    0.06
    Act Density 0.036%

    No Known Activations