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

    Neuronpedia

    INDEX
    Explanations

    These

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     klient
    -0.07
    bz
    -0.07
    ัค
    -0.07
    ована
    -0.06
    руд
    -0.06
     pravidel
    -0.06
    不
    -0.06
     Hãy
    -0.06
    {}.
    -0.06
     lidí
    -0.06
    POSITIVE LOGITS
     ded
    0.06
     Observable
    0.06
     upgraded
    0.06
     Ging
    0.06
    -token
    0.06
    asonic
    0.06
     These
    0.06
     innovation
    0.06
     Smoking
    0.06
     lint
    0.06
    Act Density 0.057%

    No Known Activations