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

    Neuronpedia

    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    载
    0.46
    ฮ
    0.45
    厛
    0.43
     związ
    0.43
     sä
    0.42
    bruck
    0.42
    EmbeddedResource
    0.42
    高志森
    0.41
     spør
    0.40
    ช่วยเหลือ
    0.40
    POSITIVE LOGITS
     class
    0.52
     aqui
    0.52
     cyclists
    0.51
     during
    0.49
     complete
    0.49
              
    0.49
     to
    0.49
     cyanide
    0.48
     actively
    0.47
     washers
    0.47
    Act Density 0.005%

    No Known Activations