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

    Neuronpedia

    INDEX
    Explanations

    predicting center points and pose estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    segments
    0.41
    feature
    0.40
    シーン
    0.39
    Polit
    0.38
    礙
    0.37
     segments
    0.36
    urgence
    0.36
     காட்சிகள்
    0.36
    Segment
    0.36
    sections
    0.35
    POSITIVE LOGITS
     predicts
    0.51
     predicting
    0.49
    预测
    0.46
     predicted
    0.45
     heatmap
    0.44
     Heat
    0.44
     Predicting
    0.44
    HEAT
    0.43
    予測
    0.43
     predict
    0.43
    Act Density 0.025%

    No Known Activations