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

    Neuronpedia

    INDEX
    Explanations

    questions, opinions, arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Techniques
    -0.08
    incre
    -0.06
    ari
    -0.06
    .ArrayAdapter
    -0.06
    diet
    -0.06
    elfast
    -0.06
     культу
    -0.06
     professionals
    -0.06
    _callbacks
    -0.06
     NOTIFY
    -0.06
    POSITIVE LOGITS
    える
    0.08
    ัย
    0.06
    часно
    0.06
    现在
    0.06
     CHK
    0.06
     کامل
    0.06
    /load
    0.06
    rical
    0.06
    -cost
    0.06
    -pointer
    0.06
    Act Density 0.005%

    No Known Activations