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

    Neuronpedia

    INDEX
    Explanations

    neural network training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plasma
    0.76
     Plasma
    0.68
    మిక
    0.66
     Mathematic
    0.64
    ushchev
    0.64
    コピー
    0.63
    াইয়া
    0.63
    Serum
    0.62
    抄
    0.62
    Plasma
    0.62
    POSITIVE LOGITS
     training
    5.81
    Training
    5.61
     Training
    5.61
    training
    5.23
    训练
    4.87
     TRAINING
    4.76
     trainings
    4.51
     Trainings
    4.40
     प्रशिक्षण
    4.37
    培训
    4.32
    Act Density 0.594%

    No Known Activations