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

    Neuronpedia

    INDEX
    Explanations

    in the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    召
    -0.07
    是一
    -0.06
    ’aut
    -0.06
    inue
    -0.06
     luận
    -0.06
    .buffer
    -0.06
     مربوط
    -0.06
    姆
    -0.06
    าค
    -0.06
     tuition
    -0.06
    POSITIVE LOGITS
     The
    0.13
    The
    0.10
     In
    0.09
     This
    0.07
     erot
    0.06
    :\/\/
    0.06
    ERRQ
    0.06
    ={!
    0.06
     noexcept
    0.06
    :CGRect
    0.06
    Act Density 0.482%

    No Known Activations