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

    Neuronpedia

    INDEX
    Explanations

    Gemma team at Google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     વૃ
    0.38
     അയാൾ
    0.37
     വൃ
    0.37
     constipation
    0.36
     defaul
    0.35
     veines
    0.34
     venous
    0.34
     bure
    0.34
    မျက်
    0.33
     if
    0.33
    POSITIVE LOGITS
    tensorflow
    0.57
     OpenAI
    0.57
    チーム
    0.52
     NVIDIA
    0.51
    team
    0.49
     टीम
    0.49
     conçu
    0.48
    Team
    0.46
     TensorFlow
    0.46
     நிறுவனம்
    0.45
    Act Density 0.255%

    No Known Activations