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

    Neuronpedia

    INDEX
    Explanations

    Formal documents and addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TER
    -0.07
    perty
    -0.07
    냐
    -0.06
     任
    -0.06
    belt
    -0.06
     edin
    -0.06
     brink
    -0.06
    -taking
    -0.06
    IVA
    -0.06
    _OT
    -0.06
    POSITIVE LOGITS
    /*.
    0.08
    .intersection
    0.07
    .strategy
    0.07
     novamente
    0.07
    我们的
    0.07
     dropped
    0.06
     admins
    0.06
    DropDown
    0.06
    -bottom
    0.06
    断
    0.06
    Act Density 0.014%

    No Known Activations