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

    Neuronpedia

    INDEX
    Explanations

    training and learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িস্থ
    0.71
     alap
    0.62
     بانک
    0.60
    흡
    0.59
    বিচার
    0.58
     banque
    0.58
     besteht
    0.55
     Natural
    0.54
     bank
    0.54
     naturelle
    0.53
    POSITIVE LOGITS
     Training
    1.08
    Training
    1.08
     training
    1.05
     Trainings
    1.02
    training
    0.93
     Trainer
    0.90
     Trains
    0.86
    训练
    0.85
     trainers
    0.85
     trainer
    0.83
    Act Density 0.470%

    No Known Activations