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

    Neuronpedia

    INDEX
    Explanations

    Mathematical/coding notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mirror
    -0.07
     symmetry
    -0.06
    иров
    -0.06
     분
    -0.06
     وابسته
    -0.06
     trả
    -0.06
    .edge
    -0.06
    cai
    -0.06
    aghetti
    -0.06
    _arrays
    -0.06
    POSITIVE LOGITS
     drought
    0.06
     withdraw
    0.06
    keeping
    0.06
    таб
    0.06
    ूड
    0.06
     sharedPreferences
    0.06
     dựa
    0.06
    sons
    0.06
    _Ch
    0.06
    ností
    0.06
    Act Density 0.141%

    No Known Activations