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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Protein
    0.52
    gramModel
    0.50
    JSPA
    0.50
    راتكم
    0.48
     оказыва
    0.48
     प्रोटीन
    0.47
    гель
    0.47
    พาะ
    0.46
     proteine
    0.45
     лечения
    0.45
    POSITIVE LOGITS
     or
    0.68
    (){
    0.57
    ？
    0.57
     is
    0.57
     {
    0.55
     ()
    0.54
    z
    0.54
    io
    0.53
    is
    0.52
    ()
    0.52
    Act Density 0.040%

    No Known Activations